<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
    <title>ai-agent</title>
    <link rel="self" type="application/atom+xml" href="https://links.biapy.com/guest/tags/3/feed"/>
    <updated>2026-06-15T08:41:52+00:00</updated>
    <id>https://links.biapy.com/guest/tags/3/feed</id>
            <entry>
            <id>https://links.biapy.com/links/13009</id>
            <title type="text"><![CDATA[MiMo Code :cn:]]></title>
            <link rel="alternate" href="https://mimo.xiaomi.com/mimocode" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13009"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A next-generation AI coding assistant for developers. Unlimited context lets you understand, build, and collaborate more efficiently.

- [MiMo Code @ GitHub](https://github.com/XiaomiMiMo/MiMo-Code).]]>
            </summary>
            <updated>2026-06-12T11:45:51+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13007</id>
            <title type="text"><![CDATA[AgentsView]]></title>
            <link rel="alternate" href="https://www.agentsview.io/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13007"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A local-first desktop and web app for browsing, searching, and analyzing your past AI coding sessions. See what your agents actually did across every project.

- [AgentsView @ GitHub](https://github.com/kenn-io/agentsview).]]>
            </summary>
            <updated>2026-06-12T11:41:52+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12940</id>
            <title type="text"><![CDATA[zerostack]]></title>
            <link rel="alternate" href="https://gi-dellav.github.io/zerostack/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12940"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Minimal coding agent written in Rust, optimized for memory footprint and performance.

 Minimal coding agent written in Rust — ~16k LoC, 26MB binary, ~16 MB RAM (avg), ~24 MB (peak). Peak RAM ~24 MB vs ~700 MB for JS-based agents. CPU: 0.0% idle, ~1.5% under load. 

- [zerostack @ GitHub](https://github.com/gi-dellav/zerostack).]]>
            </summary>
            <updated>2026-06-05T09:31:47+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12905</id>
            <title type="text"><![CDATA[Paseo]]></title>
            <link rel="alternate" href="https://paseo.sh/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12905"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Run Claude Code, Codex, Copilot, OpenCode from anywhere.

Run any coding agent from your phone, desktop, or terminal. Self-hosted, multi-provider, open source.

- [Paseo @ GitHub](https://github.com/getpaseo/paseo:).]]>
            </summary>
            <updated>2026-06-03T11:39:40+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12899</id>
            <title type="text"><![CDATA[Sandcastle]]></title>
            <link rel="alternate" href="https://github.com/mattpocock/sandcastle" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12899"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Orchestrate sandboxed coding agents in TypeScript with sandcastle.run().

A TypeScript library for orchestrating AI coding agents in isolated sandboxes.]]>
            </summary>
            <updated>2026-06-02T11:30:15+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12895</id>
            <title type="text"><![CDATA[Pullfrog]]></title>
            <link rel="alternate" href="https://pullfrog.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12895"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Open-source model-agnostic BYOK GitHub bot that runs in GitHub Actions.

Pullfrog is a GitHub bot that brings the full power of your favorite coding agents into GitHub. It&amp;#039;s open source and powered by GitHub Actions.

- [Pullfrog @ GitHub](https://github.com/pullfrog/pullfrog).]]>
            </summary>
            <updated>2026-06-02T06:44:33+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12877</id>
            <title type="text"><![CDATA[ghosttype]]></title>
            <link rel="alternate" href="https://github.com/xFreed0m/ghosttype" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12877"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Local forensic scanner that extracts credentials from AI tool conversation history. For authorized red team and DLP use only.
 
Local forensic scanner that extracts and verifies credentials from AI tool conversation history. Detection + verification powered by TruffleHog.]]>
            </summary>
            <updated>2026-06-01T15:50:55+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12845</id>
            <title type="text"><![CDATA[auth.md]]></title>
            <link rel="alternate" href="https://workos.com/auth-md" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12845"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Enable agents to register users without the sign-up form. Auth.md provides secure agent registration that any app can implement.

 An open protocol that lets agents register for services on behalf of users — discoverable through a Markdown file at your domain. 

- [auth.md @ GitHub](https://github.com/workos/auth.md).]]>
            </summary>
            <updated>2026-05-25T11:20:23+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12834</id>
            <title type="text"><![CDATA[omp]]></title>
            <link rel="alternate" href="https://omp.sh/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12834"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[a coding agent with the IDE wired in.

 ⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more 

- [omp @ GitHub](https://github.com/can1357/oh-my-pi).]]>
            </summary>
            <updated>2026-05-25T06:24:51+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12814</id>
            <title type="text"><![CDATA[Sandbox Agent SDK]]></title>
            <link rel="alternate" href="https://sandboxagent.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12814"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Run Coding Agents in Sandboxes. Control Them Over HTTP. Supports Claude Code, Codex, OpenCode, and Amp.

- [Sandbox Agent SDK @ GitHub](https://github.com/rivet-dev/sandbox-agent).

Related contents:

- [We Reverse-Engineered Docker Sandbox&amp;#039;s Undocumented MicroVM API @ Rivet](https://rivet.dev/blog/2026-02-04-we-reverse-engineered-docker-sandbox-undocumented-microvm-api/).]]>
            </summary>
            <updated>2026-05-22T16:09:11+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12776</id>
            <title type="text"><![CDATA[Superserve]]></title>
            <link rel="alternate" href="https://www.superserve.ai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12776"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Persistent &amp;amp; Secure sandboxes for AI agents.

Give your agents lightning-fast sandboxes with persistent state and versioned filesystems.

- [Superserve @ GitHub](https://github.com/superserve-ai/superserve).]]>
            </summary>
            <updated>2026-05-15T15:14:12+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12770</id>
            <title type="text"><![CDATA[Coding Agent Hooks by Sondera]]></title>
            <link rel="alternate" href="https://github.com/sondera-ai/sondera-coding-agent-hooks" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12770"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Hooking implementations and supporting tools for various coding agents (Claude, Cursor, Gemini, etc).

A reference monitor for AI coding agents. Rust hook binaries and Cedar policies intercept every shell command, file operation, and web request to forbid exfiltration and destructive behaviors, and enforce information flow control. YARA signatures and Cedar policy evaluation are deterministic; the optional LLM-based classifiers (data sensitivity, secure code policy) are probabilistic.

Related contents:

- [How to Stop Claude Code from Leaking Sensitive Data @ Secure Trajectories by Sondera](https://blog.sondera.ai/p/claude-code-data-leaks-security).]]>
            </summary>
            <updated>2026-05-15T14:14:07+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12762</id>
            <title type="text"><![CDATA[9Router]]></title>
            <link rel="alternate" href="https://9router.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12762"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Free AI Router. Smart Fallback for Claude, Codex &amp;amp; More.

 Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via 40+ providers. Auto-fallback, RTK -40% tokens, never hit limits. 

- [9Router @ GitHub](https://github.com/decolua/9router).]]>
            </summary>
            <updated>2026-05-15T11:06:14+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12744</id>
            <title type="text"><![CDATA[Agent Safehouse]]></title>
            <link rel="alternate" href="https://agent-safehouse.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12744"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Go full --yolo. We&amp;#039;ve got you.

macOS-native sandboxing for local agents. Move fast, break nothing.
 Sandbox your local AI agents so they can read/write only what they need 

- [Agent Safehouse @ GitHub](https://github.com/eugene1g/agent-safehouse).

Related contents:

- [Agent Safehouse - Un garde-fou pour vos agents IA sur macOS @ Korben :fr:](https://korben.info/agent-safehouse-garde-fou-agents-ia-macos.html).]]>
            </summary>
            <updated>2026-05-15T08:31:49+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12725</id>
            <title type="text"><![CDATA[Regent]]></title>
            <link rel="alternate" href="https://www.re-gent.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12725"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Version Control for AI agent activity.
Track what your agent did, which prompt wrote each line, and inspect any step. 

Undo, blame, checkout, and replay AI coding sessions locally. Regent captures every agent action so you stay in control.

- [Regent @ GitHub](https://github.com/regent-vcs/re_gent).]]>
            </summary>
            <updated>2026-05-14T21:05:41+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12722</id>
            <title type="text"><![CDATA[e2a]]></title>
            <link rel="alternate" href="https://e2a.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12722"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Authenticated Email for AI Agents.
Give your agent an email address. In under two minutes.

Anyone can send an email, so your agent should have one. No mail server. No public URL. Free.

 Authenticated email gateway for AI agents — SPF/DKIM verified inbound, HMAC-signed delivery, webhook + WebSocket fan-out, CLI + SDKs 

- [e2a  @ GitHub](https://github.com/Mnexa-AI/e2a).]]>
            </summary>
            <updated>2026-05-14T19:32:50+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12710</id>
            <title type="text"><![CDATA[holaOS —]]></title>
            <link rel="alternate" href="https://www.holaos.ai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12710"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Build a workspace for work that unfolds over time.
The Computer for You and Your Agent.

Describe one long-running job. Download holaOS, kick it off in seconds, and a workspace builds itself — with goals, context, rules, and a next run.

- [holaOS @ GitHub](https://github.com/holaboss-ai/holaOS).]]>
            </summary>
            <updated>2026-05-14T14:52:50+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12701</id>
            <title type="text"><![CDATA[Open Agents]]></title>
            <link rel="alternate" href="https://open-agents.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12701"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[An open source template for building cloud agents. 

Spawn coding agents that run infinitely in the cloud. Powered by AI SDK, Gateway, Sandbox, and Workflow SDK.

- [Open Agents @ GitHub](https://github.com/vercel-labs/open-agents).]]>
            </summary>
            <updated>2026-05-14T11:04:21+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12700</id>
            <title type="text"><![CDATA[context-mode]]></title>
            <link rel="alternate" href="https://context-mode.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12700"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Save 98% of your AI coding agent&amp;#039;s context window.

 Context window optimization for AI coding agents. Sandboxes tool output, 98% reduction. 15 platforms 

- [context-mode @ GitHub](https://github.com/mksglu/context-mode).]]>
            </summary>
            <updated>2026-05-14T10:41:37+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12699</id>
            <title type="text"><![CDATA[Pipelock]]></title>
            <link rel="alternate" href="https://pipelab.org/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12699"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Open-source agent firewall for MCP and AI agent egress

Pipelock enforces MCP, HTTP, and WebSocket egress at the network boundary and produces verifiable audit evidence for every inspected action.

- [Pipelock @ GitHub](https://github.com/luckyPipewrench/pipelock).

Related contents:

- [Pipelock: Open-source AI agent firewall @ Help Net Security](https://www.helpnetsecurity.com/2026/05/04/pipelock-open-source-ai-agent-firewall/).]]>
            </summary>
            <updated>2026-05-14T10:37:51+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12694</id>
            <title type="text"><![CDATA[agent-desktop]]></title>
            <link rel="alternate" href="https://github.com/lahfir/agent-desktop" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12694"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Native desktop automation CLI for AI agents. Control any application through OS accessibility trees with structured JSON output and deterministic element refs. 

agent-desktop is a native desktop automation CLI designed for AI agents, built with Rust. It gives structured access to any application through OS accessibility trees — no screenshots, no pixel matching, no browser required.]]>
            </summary>
            <updated>2026-05-14T09:36:53+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12693</id>
            <title type="text"><![CDATA[acai.sh]]></title>
            <link rel="alternate" href="https://acai.sh/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12693"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A toolkit for spec-driven software development. Stop writing prompts, start writing specs. Ship better quality software and minimize slop.

- [Acai Server @ GitHub](https://github.com/acai-sh/server).
- [Acai.sh @ GitHub](https://github.com/acai-sh/cli).]]>
            </summary>
            <updated>2026-05-14T09:35:37+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12678</id>
            <title type="text"><![CDATA[Obscura]]></title>
            <link rel="alternate" href="https://github.com/h4ckf0r0day/obscura" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12678"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The headless browser for AI agents and web scraping.
 Lightweight, stealthy, and built in Rust. 

Obscura is a headless browser engine written in Rust, built for web scraping and AI agent automation. It runs real JavaScript via V8, supports the Chrome DevTools Protocol, and acts as a drop-in replacement for headless Chrome with Puppeteer and Playwright.]]>
            </summary>
            <updated>2026-05-14T08:05:28+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12671</id>
            <title type="text"><![CDATA[pu.sh]]></title>
            <link rel="alternate" href="https://pu.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12671"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[zero package dependencies, under 50KB.
a slop cannon small enough to fit your pocket.

A zero-package-dependency coding agent under 50KB. Pronounced exactly how you think.

- [pu.sh @ GitHub](https://github.com/NahimNasser/pu).]]>
            </summary>
            <updated>2026-05-14T07:28:43+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12650</id>
            <title type="text"><![CDATA[ML Intern]]></title>
            <link rel="alternate" href="https://github.com/huggingface/ml-intern" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12650"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models 

An ML intern that autonomously researches, writes, and ships good quality ML related code using the Hugging Face ecosystem — with deep access to docs, papers, datasets, and cloud compute.]]>
            </summary>
            <updated>2026-04-29T14:22:10+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12644</id>
            <title type="text"><![CDATA[Warp]]></title>
            <link rel="alternate" href="https://www.warp.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12644"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The Agentic Development Environment.

Warp is an agentic development environment, born out of the terminal. Use Warp&amp;#039;s built-in coding agent, or bring your own CLI agent (Claude Code, Codex, Gemini CLI, and others).]]>
            </summary>
            <updated>2026-04-29T11:48:45+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12638</id>
            <title type="text"><![CDATA[Dirac]]></title>
            <link rel="alternate" href="https://dirac.run/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12638"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The Token-Efficient Coding Agent.

Coding Agent singularly focused efficiency and context curation. Reduces API costs by 50-80% vs other agent AND improves the code quality at the same time. Uses Hash Anchored edits, massively parallel operations, AST manipulation and many many other optimizations. 

- [Dirac @ GitHub](https://github.com/dirac-run/dirac).]]>
            </summary>
            <updated>2026-04-28T11:37:10+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12637</id>
            <title type="text"><![CDATA[Chainlink]]></title>
            <link rel="alternate" href="https://github.com/dollspace-gay/chainlink" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12637"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A CLI issue tracker for AI Agents.

A simple, lean issue tracker CLI designed for AI-assisted development. Track tasks across sessions with context preservation.

Related contents:

- [Agent Memory Patterns @ Tim Kellogg](https://timkellogg.me/blog/2026/04/27/memory-patterns).]]>
            </summary>
            <updated>2026-04-28T11:23:58+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12627</id>
            <title type="text"><![CDATA[cua]]></title>
            <link rel="alternate" href="https://cua.ai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12627"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Build, benchmark, and deploy agents that use computers.

 Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows). 

- [Cua @ GitHub](https://github.com/trycua/cua).]]>
            </summary>
            <updated>2026-04-27T12:08:15+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12620</id>
            <title type="text"><![CDATA[CrabTrap]]></title>
            <link rel="alternate" href="https://www.brex.com/crabtrap" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12620"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[An LLM-as-a-judge HTTP proxy to secure agents in production .

Deploy agents. Safely.
CrabTrap is an LLM-as-a-judge HTTP proxy to secure agents in production. It intercepts every request your AI agent makes, evaluates it against a policy, and allows or blocks it in real time.

- [CrabTrap @ GitHub](https://github.com/brexhq/CrabTrap).]]>
            </summary>
            <updated>2026-04-24T13:42:49+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12618</id>
            <title type="text"><![CDATA[Is Your Site Agent-Ready?]]></title>
            <link rel="alternate" href="https://isitagentready.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12618"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Scan your website to see how ready it is for AI agents. We check multiple emerging standards — from robots.txt and Markdown negotiation to MCP, OAuth, Agent Skills and agentic commerce.]]>
            </summary>
            <updated>2026-04-24T13:34:20+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12604</id>
            <title type="text"><![CDATA[Argent]]></title>
            <link rel="alternate" href="https://argent.swmansion.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12604"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Close the loop with Argent
Agentic AI Toolkit for React Native &amp;amp; Swift.
 An agentic toolkit to control, debug, and profile the iOS Simulator. Made by Software Mansion. 

An agentic toolkit to control, debug, and profile the iOS Simulator. Your agent can navigate your app, explore the component tree, inspect network requests, and trace performance problems in your mobile apps.

- [Argent @ GitHub](https://github.com/software-mansion/argent).]]>
            </summary>
            <updated>2026-04-23T11:47:57+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12523</id>
            <title type="text"><![CDATA[tui-use]]></title>
            <link rel="alternate" href="https://github.com/onesuper/tui-use" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12523"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Like BrowserUse, but for the terminal.

tui-use lets agents interact with programs that expect a human at the keyboard — REPLs, debuggers, TUI apps, and anything else bash can&amp;#039;t reach.]]>
            </summary>
            <updated>2026-04-13T04:05:43+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12480</id>
            <title type="text"><![CDATA[Agent Governance Toolkit]]></title>
            <link rel="alternate" href="https://github.com/microsoft/agent-governance-toolkit" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12480"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10. 

Runtime governance for AI agents — the only toolkit covering all 10 OWASP Agentic risks with 9,500+ tests. Governs what agents do, not just what they say — deterministic policy enforcement, zero-trust identity, execution sandboxing, and SRE — Python · TypeScript · .NET · Rust · Go

Related contents:

- [Introducing the Agent Governance Toolkit: Open-source runtime security for AI agents @ Microsoft Open Source Blog](https://opensource.microsoft.com/blog/2026/04/02/introducing-the-agent-governance-toolkit-open-source-runtime-security-for-ai-agents/).
- [Microsoft&amp;#039;s Newest Open-Source Project: Runtime Security For AI Agents @ Phoronix](https://www.phoronix.com/news/Microsoft-AI-Agent-Governance).
- [Episode 661: Sink Your Claws In @ Linux Unplugged](https://linuxunplugged.com/661).]]>
            </summary>
            <updated>2026-04-09T06:18:17+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12461</id>
            <title type="text"><![CDATA[Hazmat]]></title>
            <link rel="alternate" href="https://github.com/dredozubov/hazmat" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12461"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Full autonomy. Controlled environment.
OS-level containment for AI coding agents on macOS.

 macOS containment for AI agents — user isolation, kernel sandbox, pf firewall, DNS blocklist, backup/rollback. TLA+ verified.

AI coding agents are most useful when you let them work autonomously. But full autonomy means the agent runs with your full privileges, your credentials, your files.

Hazmat makes that safe.

Related contents:

- [Hazmat - Vos agents IA en cage sous macOS @ Korben :fr:](https://korben.info/hazmat-sandbox-macos-agents-ia.html).]]>
            </summary>
            <updated>2026-04-13T09:17:43+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12457</id>
            <title type="text"><![CDATA[What I Learned Building Real Projects with AI Coding Agents]]></title>
            <link rel="alternate" href="https://github.com/sebsto/ai-coding-lessons-learned/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12457"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A 30-minute talk sharing practical lessons from building real production projects with AI coding agents — from brainstorming to shipped code.

Related contents:

- [Episode du 7 avril @ Les Technos :fr:](https://lestechnos.be/les-technos-episode-du-7-avril/).]]>
            </summary>
            <updated>2026-04-08T05:38:19+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12456</id>
            <title type="text"><![CDATA[Git AI]]></title>
            <link rel="alternate" href="https://usegitai.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12456"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Track AI Code all the way to production

An open-source Git extension for tracking AI code through the entire SDLC.
Once installed, it automatically links every AI-written line to the agent, model, and transcripts that generated it — so you never lose the intent, requirements, and architecture decisions behind your code.

- [Git AI @ GitHub](https://github.com/git-ai-project/git-ai).]]>
            </summary>
            <updated>2026-04-07T14:37:05+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12434</id>
            <title type="text"><![CDATA[goose]]></title>
            <link rel="alternate" href="https://goose-docs.ai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12434"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM.

goose is your on-machine AI agent, capable of automating complex development tasks from start to finish. More than just code suggestions, goose can build entire projects from scratch, write and execute code, debug failures, orchestrate workflows, and interact with external APIs - autonomously.

- [goose @ GitHub](https://github.com/aaif-goose/goose).

Related contents:

- [Episode 661: Sink Your Claws In @ Linux Unplugged](https://linuxunplugged.com/661).]]>
            </summary>
            <updated>2026-04-09T06:08:49+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12407</id>
            <title type="text"><![CDATA[Phantom]]></title>
            <link rel="alternate" href="https://www.ghostwright.dev/phantom" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12407"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[our Own AI Co-Worker.
Its own computer.

Phantom deploys to a dedicated machine, learns from every conversation, and evolves its own capabilities. Open source. Self-hosted or managed.

- [Phantom @ GitHub](https://github.com/ghostwright/phantom).]]>
            </summary>
            <updated>2026-04-03T17:02:38+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12406</id>
            <title type="text"><![CDATA[smux]]></title>
            <link rel="alternate" href="https://github.com/ShawnPana/smux" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12406"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[tmux config with built-in terminal automation and agent-to-agent communication.]]>
            </summary>
            <updated>2026-04-03T16:57:20+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12405</id>
            <title type="text"><![CDATA[pGenie]]></title>
            <link rel="alternate" href="https://pgenie.io/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12405"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Write SQL. Ship confidence.
SQL-first tooling for PostgreSQL
Type-safe PostgreSQL client code generator.

pGenie validates SQL, manages indexes, and generates type-safe client SDKs — all derived from the migrations and queries in plain SQL. 

- [pGenie @ GitHub](https://github.com/pgenie-io/pgenie).]]>
            </summary>
            <updated>2026-04-03T16:43:38+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12395</id>
            <title type="text"><![CDATA[agents-anywhere]]></title>
            <link rel="alternate" href="https://github.com/alejandrobailo/agents-anywhere" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12395"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Your AI agent configs, skills, and instructions on every device. 
 One config repo. Every agent. Every machine. 

You&amp;#039;ve spent hours perfecting your CLAUDE.md, building custom skills, tuning your settings. Then you open your laptop and none of it is there. Or you switch from Claude Code to Codex and start from scratch.
agents-anywhere keeps your agent setup in a git repo and symlinks it to every agent on every machine.]]>
            </summary>
            <updated>2026-04-03T13:31:37+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12387</id>
            <title type="text"><![CDATA[Claw Code]]></title>
            <link rel="alternate" href="https://github.com/ultraworkers/claw-code" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12387"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Rewrite of Claude Code

 The fastest repo in history to surpass 50K stars ⭐, reaching the milestone in just 2 hours after publication. Better Harness Tools that make real things done. Now writing in Rust using oh-my-codex. 

Related contents:

- [Diving into Claude Code&amp;#039;s Source Code Leak @ Engineer&amp;#039;s Codex](https://read.engineerscodex.com/p/diving-into-claude-codes-source-code).]]>
            </summary>
            <updated>2026-04-03T12:59:32+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12377</id>
            <title type="text"><![CDATA[jai]]></title>
            <link rel="alternate" href="https://jai.scs.stanford.edu/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12377"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Go hard on agents, not on your filesystem.
easy containment for AI agents.

Use jai for effortless containment of AI agents on Linux.
jai strives to be the easiest container in the world to configure--so easy that you never again need to run a code assistant without protection. It&amp;#039;s not a substitute for docker or podman when you need better isolation. But if you regularly do risky things like run an AI CLI with your own privileges in your home directory on a computer that you care about, then jai could reduce the damage when things go wrong.

- [jai @ GitHub](https://github.com/stanford-scs/jai).]]>
            </summary>
            <updated>2026-03-30T18:50:49+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12351</id>
            <title type="text"><![CDATA[Expect]]></title>
            <link rel="alternate" href="https://www.expect.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12351"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Let agents test your code in a real browser.

One command scans your unstaged changes or branch diff, then generates a test plan, and runs it against a live browser.

Expect reads your unstaged changes or branch diff, sends them to an AI agent (Claude Code or Codex CLI), and generates a step-by-step test plan describing how to validate the changes. You review and approve the plan in an interactive TUI, then the agent executes each step against a live browser - using your real login sessions so there&amp;#039;s no manual auth setup. Every session is recorded so you can replay exactly what happened.

- [Expect @ GitHub](https://github.com/millionco/expect).]]>
            </summary>
            <updated>2026-03-28T18:05:46+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12330</id>
            <title type="text"><![CDATA[GSD 2]]></title>
            <link rel="alternate" href="https://github.com/gsd-build/gsd-2" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12330"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A powerful meta-prompting, context engineering and spec-driven development system that enables agents to work for long periods of time autonomously without losing track of the big picture]]>
            </summary>
            <updated>2026-03-28T08:29:43+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12314</id>
            <title type="text"><![CDATA[Arbor]]></title>
            <link rel="alternate" href="https://penso.github.io/arbor/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12314"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Run agentic coding workflows in a fully native desktop app for Git worktrees, terminals, and diffs. 
Fully Native App for Agentic Coding. Run issue-driven coding workflows in one native workspace.

Arbor is a Rust-powered native workspace with a shared daemon for the desktop app, web UI, CLI, and MCP server. Create worktrees from issues, run embedded terminals and managed processes, inspect PR context, and keep coding agents visible without juggling tools. 

- [Arbor @ GitHub](https://github.com/penso/arbor).]]>
            </summary>
            <updated>2026-03-28T07:39:32+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12295</id>
            <title type="text"><![CDATA[Optio]]></title>
            <link rel="alternate" href="https://github.com/jonwiggins/optio" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12295"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Workflow orchestration for AI coding agents, from task to merged PR. 

Optio turns coding tasks into merged pull requests — without human babysitting. Submit a task (manually, from a GitHub Issue, or from Linear), and Optio handles the rest: provisions an isolated environment, runs an AI agent, opens a PR, monitors CI, triggers code review, auto-fixes failures, and merges when everything passes.]]>
            </summary>
            <updated>2026-03-26T12:54:06+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12279</id>
            <title type="text"><![CDATA[Vapi]]></title>
            <link rel="alternate" href="https://vapi.ai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12279"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Build Advanced Voice AI Agents.

Related contents:

- [How I Built an AI Receptionist for a Luxury Mechanic Shop - Part 1 @ That Ladydev](https://www.itsthatlady.dev/blog/building-an-ai-receptionist-for-my-brother/).]]>
            </summary>
            <updated>2026-03-24T13:48:29+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12274</id>
            <title type="text"><![CDATA[cq]]></title>
            <link rel="alternate" href="https://github.com/mozilla-ai/cq" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12274"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[An open standard for shared agent learning. Agents persist, share, and query collective knowledge so they stop rediscovering the same failures independently. 

cq is derived from colloquy (/ˈkɒl.ə.kwi/), a structured exchange of ideas where understanding emerges through dialogue rather than one-way output. It reflects a focus on reciprocal knowledge sharing; systems that improve through participation, not passive use. In radio, CQ is a general call (&amp;quot;any station, respond&amp;quot;), capturing the same model: open invitation, response, and collective signal built through interaction.

Related contents:

- [cq: Stack Overflow for Agents @ Mozilla.ai](https://blog.mozilla.ai/cq-stack-overflow-for-agents/).]]>
            </summary>
            <updated>2026-03-24T13:25:02+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12271</id>
            <title type="text"><![CDATA[Claude Code]]></title>
            <link rel="alternate" href="https://claude.com/product/claude-code" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12271"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[AI Coding Agent, Terminal, IDE.

Work with Claude directly in your codebase. Build, debug, and ship from your terminal, IDE, Slack, or the web. Describe what you need, and Claude handles the rest.

Related contents:

- [Claude Code Cheat Sheet](https://cc.storyfox.cz/).
- [Claude Code Essentials @ freeCodeCamp.org&amp;#039;s YouTube](https://www.youtube.com/watch?v=brLhhkUqcn4).
- [How I&amp;#039;m Productive with Claude Code @ Neil Kakkar](https://neilkakkar.com/productive-with-claude-code.html).
- [Auto mode for Claude Code @ Simon Willison&amp;#039;s Weblog](https://simonwillison.net/2026/Mar/24/auto-mode-for-claude-code/#atom-everything).
- [Inside the Claude Code source @ Haseeb Qureshi&amp;#039;s GitHub Gist](https://gist.github.com/Haseeb-Qureshi/d0dc36844c19d26303ce09b42e7188c1).
- [Entire Claude Code CLI source code leaks thanks to exposed map file @ Ars Technica](https://arstechnica.com/ai/2026/03/entire-claude-code-cli-source-code-leaks-thanks-to-exposed-map-file/).
- [Reading leaked Claude Code source code @ Vita Nouva](https://lr0.org/blog/p/claude-code-source/).
- [The Claude Code Source Leak: fake tools, frustration regexes, undercover mode, and more @ Alex Kim&amp;#039;s blog](https://alex000kim.com/posts/2026-03-31-claude-code-source-leak/).
- [What&amp;#039;s cch? Reverse Engineering Claude Code&amp;#039;s Request Signing](https://a10k.co/b/reverse-engineering-claude-code-cch.html).
- [How Claude Code Builds a System Prompt @ dbreunig.com](https://www.dbreunig.com/2026/04/04/how-claude-code-builds-a-system-prompt.html).
- [Fuite Claude Code - 6 trucs à piquer pour vos hooks @ Korben :fr:](https://korben.info/claude-code-6-patterns-bonnes-pratiques-hooks.html).
- [Leveling Up Secure Code Reviews with Claude Code @ SpecterOps](https://specterops.io/blog/2026/03/26/leveling-up-secure-code-reviews-with-claude-code/).]]>
            </summary>
            <updated>2026-04-13T04:12:08+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12245</id>
            <title type="text"><![CDATA[Agent Sandbox]]></title>
            <link rel="alternate" href="https://agent-sandbox.sigs.k8s.io/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12245"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes. 

- [Agent Sandbox @ GitHub](https://github.com/kubernetes-sigs/agent-sandbox).

Related contents:

- [Running Agents on Kubernetes with Agent Sandbox @ Kubernetes blog](https://kubernetes.io/blog/2026/03/20/running-agents-on-kubernetes-with-agent-sandbox/).]]>
            </summary>
            <updated>2026-03-23T15:05:20+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12233</id>
            <title type="text"><![CDATA[Serena]]></title>
            <link rel="alternate" href="https://oraios.github.io/serena/01-about/000_intro.html" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12233"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Serena is a powerful coding agent toolkit capable of turning an LLM into a fully-featured agent that works directly on your codebase. Unlike most other tools, it is not tied to an LLM, framework or an interface, making it easy to use it in a variety of ways.

Serena provides essential semantic code retrieval and editing tools that are akin to an IDE’s capabilities, extracting code entities at the symbol level and exploiting relational structure. When combined with an existing coding agent, these tools greatly enhance (token) efficiency.

Serena is free &amp;amp; open-source, enhancing the capabilities of LLMs you already have access to free of charge.

- [Serena @ GitHub](https://github.com/oraios/serena).

Related contents:

- [\#346.src - IA &amp;amp; DevX: Code assisté, valeur humaine préservée avec Jocelyn N&amp;#039;takpe @ \&amp;lt;ifttd&amp;gt;](https://www.ifttd.io/episodes/ia-devx).]]>
            </summary>
            <updated>2026-03-22T18:16:43+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12223</id>
            <title type="text"><![CDATA[Ghost OS]]></title>
            <link rel="alternate" href="https://github.com/ghostwright/ghost-os" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12223"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Full computer-use for AI agents. Self-learning workflows. Native macOS. No screenshots required. 

Your AI agent can write code, run tests, search files. But it can&amp;#039;t click a button, send an email, or fill out a form. It lives inside a chat box.

Ghost OS changes that. One install, and any AI agent can see and operate every app on your Mac.]]>
            </summary>
            <updated>2026-03-20T14:03:05+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12216</id>
            <title type="text"><![CDATA[NVIDIA OpenShell]]></title>
            <link rel="alternate" href="https://docs.nvidia.com/openshell/latest/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12216"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[OpenShell is the safe, private runtime for autonomous AI agents. 

NVIDIA OpenShell is the safe, private runtime for autonomous AI agents. It provides sandboxed execution environments that protect your data, credentials, and infrastructure. Agents run with exactly the permissions they need and nothing more, governed by declarative policies that prevent unauthorized file access, data exfiltration, and uncontrolled network activity.

- [NVIDIA OpenShell @ GitHub](https://github.com/NVIDIA/OpenShell).]]>
            </summary>
            <updated>2026-03-20T13:48:09+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12173</id>
            <title type="text"><![CDATA[Open SWE]]></title>
            <link rel="alternate" href="https://github.com/langchain-ai/open-swe" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12173"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[An Open-Source Asynchronous Coding Agent.
Open-source framework for building your org&amp;#039;s internal coding agent.

Elite engineering orgs like Stripe, Ramp, and Coinbase are building their own internal coding agents — Slackbots, CLIs, and web apps that meet engineers where they already work. These agents are connected to internal systems with the right context, permissioning, and safety boundaries to operate with minimal human oversight.

Open SWE is the open-source version of this pattern. Built on LangGraph and Deep Agents, it gives you the same architecture those companies built internally: cloud sandboxes, Slack and Linear invocation, subagent orchestration, and automatic PR creation — ready to customize for your own codebase and workflows.

Related contents:

- [Open SWE: An Open-Source Framework for Internal Coding Agents @ LangChain Blog](https://blog.langchain.com/open-swe-an-open-source-framework-for-internal-coding-agents/).]]>
            </summary>
            <updated>2026-03-18T11:25:31+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12146</id>
            <title type="text"><![CDATA[GitAgent]]></title>
            <link rel="alternate" href="https://www.gitagent.sh/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12146"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[your repository becomes your agent.
The Open Standard for Git-Native AI Agents.
The open standard for defining, versioning, and running AI agents natively in git.

A git-native, framework-agnostic, open standard for defining AI agents. Version-controlled config that exports to Claude Code, OpenClaw, Lyzr Agent, Chimera, NanoBot, CrewAgent, and Agents SDK.

- [GitAgent @ GitHub](https://github.com/open-gitagent/gitagent).]]>
            </summary>
            <updated>2026-03-16T12:24:17+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12138</id>
            <title type="text"><![CDATA[Conductor]]></title>
            <link rel="alternate" href="https://www.conductor.build/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12138"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Run a team of coding agents on your Mac.

Create parallel Codex + Claude Code agents in isolated workspaces. See at a glance what they&amp;#039;re working on, then review and merge their changes.

Related contents:

- [Conductor - Lancez des agents IA en parallèle sur votre code @ Korben :fr:](https://korben.info/conductor-build.html).]]>
            </summary>
            <updated>2026-03-16T09:39:15+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12134</id>
            <title type="text"><![CDATA[Aegis]]></title>
            <link rel="alternate" href="https://aegisprotect.vercel.app/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12134"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Open-source EDR for AI agents.
Monitor processes, files, network, and behavior of autonomous AI agents. 
 
Aegis is an open-source endpoint detection and response (EDR) tool that monitors AI agent processes, file access, network activity, and behavioral anomalies in real time. Built with Electron 33, Svelte 5, and TypeScript, it provides the same class of oversight for autonomous AI agents that CrowdStrike provides for traditional endpoints. No telemetry. No cloud. Everything stays local.

- [AEGIS @ GitHub](https://github.com/antropos17/Aegis).]]>
            </summary>
            <updated>2026-03-16T07:49:48+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12108</id>
            <title type="text"><![CDATA[InsForge]]></title>
            <link rel="alternate" href="https://insforge.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12108"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The Backend Built forAgentic Development

Give agents everything they need
to ship fullstack apps.

InsForge is a backend development platform built for AI coding agents and AI code editors. It exposes backend primitives like databases, auth, storage, and functions through a semantic layer that agents can understand, reason about, and operate end to end.

- [InsForge @ GitHub](https://github.com/InsForge/InsForge).]]>
            </summary>
            <updated>2026-03-13T12:59:12+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12106</id>
            <title type="text"><![CDATA[Understudy]]></title>
            <link rel="alternate" href="https://understudy-ai.github.io/understudy/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12106"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Watch once. Then take the stage.
A Teachable Desktop Agent.

Understudy is a teachable desktop agent. It operates your computer like a human colleague across GUI, browser, shell, files, and messaging. You demonstrate a task once, it learns the intent, remembers successful paths, and gradually upgrades to faster execution routes. 

- [Understudy @ GitHub](https://github.com/understudy-ai/understudy).]]>
            </summary>
            <updated>2026-03-13T12:37:48+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12104</id>
            <title type="text"><![CDATA[OneCLI]]></title>
            <link rel="alternate" href="https://www.onecli.sh/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12104"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Give your agents access, not your secrets.
The open-source secret vault for AI agents.
 Store once. Inject anywhere. Agents never see the keys. 

Open-source credential vault. Your agents call services and never see a key.

OneCLI is an open-source gateway that sits between your AI agents and the services they call. Instead of baking API keys into every agent, you store credentials once in OneCLI and the gateway injects them transparently. Agents never see the secrets.

- [OneCLI @ GitHub](https://github.com/onecli/onecli).]]>
            </summary>
            <updated>2026-03-13T12:32:45+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12090</id>
            <title type="text"><![CDATA[Symphony]]></title>
            <link rel="alternate" href="https://github.com/openai/symphony" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12090"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

Related contents:

- [An open-source spec for Codex orchestration: Symphony @ OpenAI](https://openai.com/index/open-source-codex-orchestration-symphony/).]]>
            </summary>
            <updated>2026-04-28T11:39:22+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12089</id>
            <title type="text"><![CDATA[Hermes Agent]]></title>
            <link rel="alternate" href="https://hermes-agent.org/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12089"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[An agent that grows with you.

Install it on a machine, give it your messaging accounts, and it becomes a persistent personal agent that grows with you — learning your projects, building its own skills, and reaching you wherever you are. 

The self-improving AI agent built by Nous Research. It&amp;#039;s the only agent with a built-in learning loop — it creates skills from experience, improves them during use, nudges itself to persist knowledge, searches its own past conversations, and builds a deepening model of who you are across sessions. Run it on a $5 VPS, a GPU cluster, or serverless infrastructure that costs nearly nothing when idle. It&amp;#039;s not tied to your laptop — talk to it from Telegram while it works on a cloud VM.

- [Hermes Agent](https://hermes-agent.nousresearch.com/).
- [Hermes Agent @ GitHub](https://github.com/NousResearch/hermes-agent).

Related contents:

- [Episode du 7 avril @ Les Technos :fr:](https://lestechnos.be/les-technos-episode-du-7-avril/).
- [Episode 661: Sink Your Claws In @ Linux Unplugged](https://linuxunplugged.com/661).
- [Episode 668: --yolo @ Linux Unplugged](https://linuxunplugged.com/668).
- [E357: Hermes Agent: Agents that grow with you @ Practical AI](https://practicalai.show/357).]]>
            </summary>
            <updated>2026-06-03T05:37:56+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12085</id>
            <title type="text"><![CDATA[Pact]]></title>
            <link rel="alternate" href="https://github.com/jmcentire/pact" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12085"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Contracts before code. Tests as law. Agents that can&amp;#039;t cheat. 

Pact is a multi-agent software engineering framework where the architecture is decided before a single line of implementation is written. Tasks are decomposed into components, each component gets a typed interface contract, and each contract gets executable tests. Only then do agents implement -- independently, in parallel, even competitively -- with no way to ship code that doesn&amp;#039;t honor its contract. Generates Python, TypeScript, or JavaScript.]]>
            </summary>
            <updated>2026-03-11T11:06:44+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12069</id>
            <title type="text"><![CDATA[React Native Grab]]></title>
            <link rel="alternate" href="https://github.com/callstackincubator/react-native-grab" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12069"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Touch-to-grab context tool for React Native UI changes.

Bridge the context gap: point at the exact native UI element, capture precise source context, and hand it to your coding agent without guesswork.]]>
            </summary>
            <updated>2026-03-09T12:14:40+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12062</id>
            <title type="text"><![CDATA[yolobox]]></title>
            <link rel="alternate" href="https://github.com/finbarr/yolobox" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12062"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Let your AI go full send. Your home directory stays home.

Run Claude Code, Codex, or any AI coding agent in &amp;quot;yolo mode&amp;quot; without nuking your home directory.

Related contents:

- [Yolobox - Lâchez vos agents IA sauvages sans flinguer votre home @ Korben :fr:](https://korben.info/yolobox-sandbox-ia-agents.html).]]>
            </summary>
            <updated>2026-03-09T09:55:04+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12055</id>
            <title type="text"><![CDATA[no-agents.md]]></title>
            <link rel="alternate" href="https://codeberg.org/rossabaker/no-agents.md" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12055"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A project to reject AI agents via AGENTS.md.
This project provides the context and instructions to AI agents that their presence is unwelcome.

Related contents:

- [no-agents.md - Le fichier qui dit non aux IA dans votre code @ Korben :fr:](https://korben.info/no-agents-md-bloquer-ia-repo.html).]]>
            </summary>
            <updated>2026-03-09T09:25:17+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12051</id>
            <title type="text"><![CDATA[Infrastructure Agents Guide]]></title>
            <link rel="alternate" href="https://github.com/Cloudgeni-ai/infrastructure-agents-guide" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12051"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[How to design, build, and operate AI agents for infrastructure teams — safely. 13 chapters covering architecture, sandboxing, credentials, change control, observability, and more. 

AI agents can write IaC, fix compliance findings, detect drift, review PRs, and respond to incidents — all autonomously. But autonomy without guardrails is a liability. Agents that can terraform apply can also terraform destroy. Agents that read configs can leak secrets. Agents that loop can burn budgets.

This guide covers every architectural decision you need to make when building infrastructure agents — with real patterns, code snippets, multiple alternatives, and the risk framework to evaluate your choices.]]>
            </summary>
            <updated>2026-03-09T07:28:09+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12042</id>
            <title type="text"><![CDATA[ReMe]]></title>
            <link rel="alternate" href="https://github.com/agentscope-ai/ReMe" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12042"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Memory Management Kit for Agents - Remember Me, Refine Me. 

🧠 ReMe is a memory management framework built for AI agents, offering both file-based and vector-based memory systems.

It addresses two core problems of agent memory: limited context windows (early information gets truncated or lost during long conversations) and stateless sessions (new conversations cannot inherit history and always start from scratch).

ReMe gives agents real memory — old conversations are automatically condensed, important information is persisted, and the next conversation can recall it automatically.]]>
            </summary>
            <updated>2026-03-06T12:47:50+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12000</id>
            <title type="text"><![CDATA[ClawShield]]></title>
            <link rel="alternate" href="https://github.com/SleuthCo/clawshield-public" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12000"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Security proxy for AI agents. Scans every message for prompt injection, PII, and secrets. Defense-in-depth: Go proxy + iptables firewall + eBPF kernel monitor. YAML policy engine, audit logging, 5 AI agents with RAG knowledge bases. 

Security proxy for AI agents. Sits in front of OpenClaw and scans every message for prompt injection, PII leaks, and secrets — before they reach the model or leave the network.]]>
            </summary>
            <updated>2026-03-03T13:50:07+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11988</id>
            <title type="text"><![CDATA[Superset]]></title>
            <link rel="alternate" href="https://superset.sh/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11988"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The Terminal for Coding Agents.

IDE for the AI Agents Era - Run an army of Claude Code, Codex, etc. on your machine.
Superset is a turbocharged terminal that allows you to run any CLI coding agents along with the tools to 10x your development workflow.

- [Superset @ GitHub](https://github.com/superset-sh/superset).]]>
            </summary>
            <updated>2026-03-02T12:51:19+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11985</id>
            <title type="text"><![CDATA[MemU]]></title>
            <link rel="alternate" href="https://memu.pro/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11985"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Memory for Proactive 24/7 Agents.

MemU powers autonomous AI agents with persistent, evolving memory.
Continuously predict user intentions, act proactively, and work for you — even while you sleep.

- [MemU @ GitHub](https://github.com/NevaMind-AI/memU).]]>
            </summary>
            <updated>2026-03-02T12:41:42+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11984</id>
            <title type="text"><![CDATA[Mistral Vibe :fr:]]></title>
            <link rel="alternate" href="https://github.com/mistralai/mistral-vibe" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11984"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Minimal CLI coding agent by Mistral.

Mistral Vibe is a command-line coding assistant powered by Mistral&amp;#039;s models. It provides a conversational interface to your codebase, allowing you to use natural language to explore, modify, and interact with your projects through a powerful set of tools.]]>
            </summary>
            <updated>2026-03-02T12:35:56+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11972</id>
            <title type="text"><![CDATA[OpenSwarm]]></title>
            <link rel="alternate" href="https://github.com/Intrect-io/OpenSwarm" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11972"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[CLI Code Agent Orchestrator. Autonomous AI agent orchestrator powered by Claude Code CLI.

OpenSwarm orchestrates multiple Claude Code instances as autonomous agents. It picks up Linear issues, runs Worker/Reviewer pair pipelines to produce code changes, reports progress to Discord, and retains long-term memory via LanceDB vector embeddings.]]>
            </summary>
            <updated>2026-03-02T06:55:24+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11970</id>
            <title type="text"><![CDATA[Mission Control]]></title>
            <link rel="alternate" href="https://github.com/MeisnerDan/mission-control" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11970"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Open-source task management for the agentic era.
The command center for solo entrepreneurs who delegate work to AI agents. 

 Open-source task management for the agentic era. The command center for solo entrepreneurs who delegate work to AI agents. 

Mission Control gives your AI agents structure. Agents get roles, inboxes, and reporting protocols. You delegate work through a visual dashboard, they execute and report back. You stay in control without micromanaging.]]>
            </summary>
            <updated>2026-03-02T06:52:53+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11967</id>
            <title type="text"><![CDATA[just-bash]]></title>
            <link rel="alternate" href="https://justbash.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11967"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A sandboxed bash interpreter for AI agents. Pure TypeScript with in-memory filesystem.

A simulated bash environment with an in-memory virtual filesystem, written in TypeScript.
Designed for AI agents that need a secure, sandboxed bash environment.
Supports optional network access via curl with secure-by-default URL filtering.

- [just-bash @ GitHub](https://github.com/vercel-labs/just-bash).]]>
            </summary>
            <updated>2026-03-02T06:46:20+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11887</id>
            <title type="text"><![CDATA[peon-ping]]></title>
            <link rel="alternate" href="https://www.peonping.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11887"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Game character voice lines + visual overlay notifications when your AI coding agent needs attention — or let the agent pick its own sound via MCP.

AI coding agents don&amp;#039;t notify you when they finish or need permission. You tab away, lose focus, and waste 15 minutes getting back into flow. peon-ping fixes this with voice lines and bold on-screen banners from Warcraft, StarCraft, Portal, Zelda, and more — works with Claude Code, GitHub Copilot, Codex, Cursor, OpenCode, Kilo CLI, Kiro, Windsurf, Google Antigravity, and any MCP client.

- [peon-ping @ GitHub](https://github.com/PeonPing/peon-ping).

Related contents:

- [Newsletter du 16 Février 2026 @ Rudeops :fr:](https://www.rudeops.com/newsletter/2026-02-16-rudeops-newsletter/).
- [Peon Ping - Donnez de la voix à vos agents IA @ Korben :fr:](https://korben.info/peon-ping-notifications-warcraft-agents-ia.html).]]>
            </summary>
            <updated>2026-03-23T16:23:30+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11861</id>
            <title type="text"><![CDATA[React Doctor]]></title>
            <link rel="alternate" href="https://www.react.doctor/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11861"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Let coding agents diagnose and fix your React code.

One command scans your codebase for security, performance, correctness, and architecture issues, then outputs a 0–100 score with actionable diagnostics.

- [React Doctor @ GitHub](https://github.com/millionco/react-doctor).]]>
            </summary>
            <updated>2026-02-19T13:04:15+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11858</id>
            <title type="text"><![CDATA[roborev]]></title>
            <link rel="alternate" href="https://www.roborev.io/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11858"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Continuous, non-invasive background code review for agents, to work better and faster. With TUI and CLI support.

Continuous code review for coding agents. Review commits immediately, catch issues early, and fix them while context is fresh.

- [roborev @ GitHub](https://github.com/roborev-dev/roborev).

Related contents:

- [The Mythical Agent-Month @ Wes McKinney](https://wesmckinney.com/blog/mythical-agent-month/)]]>
            </summary>
            <updated>2026-02-19T12:50:20+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11853</id>
            <title type="text"><![CDATA[Wax]]></title>
            <link rel="alternate" href="https://github.com/christopherkarani/Wax" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11853"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The SQLite for AI memory.  One file. Full RAG. Zero infrastructure. 

 🍯 Memory layer for on-device AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer.]]>
            </summary>
            <updated>2026-02-18T13:18:33+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11834</id>
            <title type="text"><![CDATA[klaw]]></title>
            <link rel="alternate" href="https://klaw.sh/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11834"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[kubectl for AI Agents.
Enterprise AI agent orchestration. Manage, monitor, and scale your AI workforce.

- [klaw @ GitHub](https://github.com/klawsh/klaw.sh).]]>
            </summary>
            <updated>2026-02-16T12:32:29+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11805</id>
            <title type="text"><![CDATA[Antfarm]]></title>
            <link rel="alternate" href="https://www.antfarm.cool/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11805"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Build your agent team in OpenClaw with one command.

You don&amp;#039;t need to hire a dev team. You need to define one. Antfarm gives you a team of specialized AI agents — planner, developer, verifier, tester, reviewer — that work together in reliable, repeatable workflows. One install. Zero infrastructure.

- [Antfarm @ GitHub](https://github.com/snarktank/antfarm).

Related contents:

- [Antfarm Patterns: Orchestrating Specialized Agent Teams for Compound Engineering @ Vinci Rufus](https://www.vincirufus.com/posts/antfarm-patterns-orchestrating-specialized-agent-teams/).]]>
            </summary>
            <updated>2026-02-13T13:04:37+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11802</id>
            <title type="text"><![CDATA[AgentLogs]]></title>
            <link rel="alternate" href="https://agentlogs.ai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11802"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Coding agents, visible to your team.  Collaboration in the age of agentic engineering .

Open-source and self-hostable. Track sessions, share prompts, and link every conversation to the commit it produced.

AgentLogs captures and analyzes transcripts from AI coding agents (like Claude Code, Codex, OpenCode, and Pi) to give your team visibility into how AI tools are used in their codebases.

- [AgentLogs @ GitHub](https://github.com/agentlogs/agentlogs).

Related contents:

- [Open-sourcing AgentLogs @ spiess.dev](https://spiess.dev/blog/open-sourcing-agentlogs).]]>
            </summary>
            <updated>2026-02-13T12:54:21+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11801</id>
            <title type="text"><![CDATA[Sidecar]]></title>
            <link rel="alternate" href="https://github.com/marcus/sidecar" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11801"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[You might never open your editor again.

Use sidecar next to CLI agents for diffs, file trees, conversation history, and task management with td.

Sidecar puts your entire development workflow in one shell: plan tasks with td, chat with AI agents, review diffs, stage commits, review past conversations, and manage workspaces—all without leaving Sidecar.]]>
            </summary>
            <updated>2026-02-13T12:51:57+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11796</id>
            <title type="text"><![CDATA[Agentic AuthZ Demo]]></title>
            <link rel="alternate" href="https://github.com/Siddhant-K-code/agentic-authz" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11796"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Fine-grained authorization for AI agents using OpenFGA. 

AI agents are getting access to production systems - databases, APIs, file systems. But who decides what they can do? Traditional RBAC wasn&amp;#039;t designed for autonomous agents that make decisions without human approval.

Related contents:

- [AI fatigue is real and nobody talks about it @ Siddhant Khare](https://siddhantkhare.com/writing/ai-fatigue-is-real).]]>
            </summary>
            <updated>2026-02-13T09:28:33+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11780</id>
            <title type="text"><![CDATA[Rodney]]></title>
            <link rel="alternate" href="https://github.com/simonw/rodney" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11780"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Chrome automation from the command line.
CLI tool for interacting with the web.

A Go CLI tool that drives a persistent headless Chrome instance using the rod browser automation library. Each command connects to the same long-running Chrome process, making it easy to script multi-step browser interactions from shell scripts or interactive use.

Related contents:

- [Introducing Showboat and Rodney, so agents can demo what they’ve built @ Simon Willison’s Weblog](https://simonwillison.net/2026/Feb/10/showboat-and-rodney/).]]>
            </summary>
            <updated>2026-02-11T13:05:14+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11779</id>
            <title type="text"><![CDATA[Showboat]]></title>
            <link rel="alternate" href="https://github.com/simonw/showboat" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11779"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Create executable demo documents that show and prove an agent&amp;#039;s work.

Showboat helps agents build markdown documents that mix commentary, executable code blocks, and captured output. These documents serve as both readable documentation and reproducible proof of work. A verifier can re-execute all code blocks and confirm the outputs still match.

Related contents:

- [Introducing Showboat and Rodney, so agents can demo what they’ve built @ Simon Willison’s Weblog](https://simonwillison.net/2026/Feb/10/showboat-and-rodney/).
- [Two new Showboat tools: Chartroom and datasette-showboat @ Simon Willison’s Weblog](https://simonwillison.net/2026/Feb/17/chartroom-and-datasette-showboat/).
- [Linear walkthroughs @ Simon Willison’s Weblog](https://simonwillison.net/guides/agentic-engineering-patterns/linear-walkthroughs/).]]>
            </summary>
            <updated>2026-02-25T12:49:36+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11777</id>
            <title type="text"><![CDATA[Shannon]]></title>
            <link rel="alternate" href="https://github.com/KeygraphHQ/shannon" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11777"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Shannon is your fully autonomous AI pentester.

Shannon’s job is simple: break your web app before anyone else does.
The Red Team to your vibe-coding Blue team.
Every Claude (coder) deserves their Shannon.

 Fully autonomous AI hacker to find actual exploits in your web apps. Shannon has achieved a 96.15% success rate on the hint-free, source-aware XBOW Benchmark.

Related contents:

- [Shannon - L&amp;#039;IA qui pentest votre code toute seule @ Korben :fr:](https://korben.info/shannon-pentester-ia-autonome.html).]]>
            </summary>
            <updated>2026-02-16T09:34:32+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11767</id>
            <title type="text"><![CDATA[Personal AI Infrastructure]]></title>
            <link rel="alternate" href="https://github.com/danielmiessler/Personal_AI_Infrastructure" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11767"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Agentic AI Infrastructure for magnifying HUMAN capabilities.  

PAI is a Personalized AI Platform designed to magnify your capabilities.

It&amp;#039;s designed for humans most of all, but can be used by teams, companies, or Federations of Planets desiring to be better versions of themselves.

The scale of the entity doesn&amp;#039;t matter: It&amp;#039;s a system for understanding, articulating, and realizing its principal&amp;#039;s goals using a full-featured Agentic AI Platform.

Related contents:

- [A Deepdive on my Personal AI Infrastructure (PAI v2.0, December 2025) @ Unsupervised Learning&amp;#039;s YouTube](https://www.youtube.com/watch?v=Le0DLrn7ta0).
- [Personal AI Infrastructure - L&amp;#039;agent intelligent qui vous connaît vraiment @ Korben :fr:](https://korben.info/personal-ai-infrastructure.html).]]>
            </summary>
            <updated>2026-02-09T16:24:24+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11764</id>
            <title type="text"><![CDATA[Matchlock]]></title>
            <link rel="alternate" href="https://github.com/jingkaihe/matchlock" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11764"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Matchlock secures AI agent workloads with a Linux-based sandbox. 

Matchlock is a CLI tool for running AI agents in ephemeral microVMs - with network allowlisting, secret injection via MITM proxy, and VM-level isolation. Your secrets never enter the VM.]]>
            </summary>
            <updated>2026-02-09T13:08:00+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11763</id>
            <title type="text"><![CDATA[agent-slack]]></title>
            <link rel="alternate" href="https://github.com/stablyai/agent-slack" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11763"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Slack automation CLI for AI agents.]]>
            </summary>
            <updated>2026-02-09T13:06:28+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11762</id>
            <title type="text"><![CDATA[GitHub Agentic Workflows]]></title>
            <link rel="alternate" href="https://github.github.io/gh-aw/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11762"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Repository automation, running the coding agents you know and love, with strong guardrails in GitHub Actions.



Use GitHub Copilot, Claude by Anthropic or OpenAI Codex for event-triggered, recurring and scheduled jobs to improve, document and analyze your repository.

- [GitHub Agentic Workflows @ GitHub](https://github.com/github/gh-aw).]]>
            </summary>
            <updated>2026-02-09T13:05:43+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11751</id>
            <title type="text"><![CDATA[Vibe]]></title>
            <link rel="alternate" href="https://github.com/lynaghk/vibe" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11751"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Easy Linux virtual machine on MacOS to sandbox LLM agents.

Vibe is a quick, zero-configuration way to spin up a Linux virtual machine on Mac to sandbox LLM agents.

Related contents:

- [Vos agents IA sécurisés en -10 sec. sur Mac @ Korben :fr:](https://korben.info/vibe-coding-terminal-llm.html).]]>
            </summary>
            <updated>2026-02-09T08:49:44+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11710</id>
            <title type="text"><![CDATA[🌊 fluid.sh]]></title>
            <link rel="alternate" href="https://www.fluid.sh/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11710"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Autonomous AI Agents for Infrastructure.
Claude Code for infrastructure. Debug, act, and audit everything Fluid does on your infrastructure. 

 Fluid is a terminal agent that do work on production infrastructure like VMs/K8s cluster/etc. by making sandbox clones of the infrastructure for AI agents to work on, allowing the agents to run commands, test connections, edit files, and then generate Infra-as-code like an Ansible Playbook to be applied on production. 

- [🌊 fluid.sh @ GitHub](https://github.com/aspectrr/fluid.sh).]]>
            </summary>
            <updated>2026-02-05T13:10:46+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11693</id>
            <title type="text"><![CDATA[Pi]]></title>
            <link rel="alternate" href="https://pi.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11693"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Pi is a minimal terminal coding harness. Adapt pi to your workflows, not the other way around, without having to fork and modify pi internals. Extend it with TypeScript Extensions, Skills, Prompt Templates, and Themes. Put your extensions, skills, prompt templates, and themes in Pi Packages and share them with others via npm or git.

- [Pi Coding Agent @ GitHub](https://github.com/badlogic/pi-mono/tree/main/packages/coding-agent).

Related contents:

- [What I learned building an opinionated and minimal coding agent @ Mario Zechner](https://mariozechner.at/posts/2025-11-30-pi-coding-agent/).
- [🦞 CRACKING THE CLAW @ CTO Lunch NYC](https://ctolunchnyc.substack.com/p/cracking-the-claw).
- [Pi: The Minimal Agent Within OpenClaw @ Armin Ronacher&amp;#039;s Thoughts and Writings](https://lucumr.pocoo.org/2026/1/31/pi/).
- [Pi: Open-Source AI Agent Terminal Set-Up @ Christian Lempa&amp;#039;s YouTube](https://www.youtube.com/watch?v=04EL2_Llenc).]]>
            </summary>
            <updated>2026-05-22T13:29:57+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11668</id>
            <title type="text"><![CDATA[Volition]]></title>
            <link rel="alternate" href="https://github.com/AIndoria/volition" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11668"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[This is a public, sanitized version of my Abiverse repository for people to use and run their own Abes.

Volition (fondly referred to me as the Abiverse) is a self-hosted, multi-agent system designed to run persistent, self-replicating autonomous LLM-based agents (&amp;quot;Abes&amp;quot;) inside isolated Linux containers. These are not chatbots, but I have aimed for them to be long-lived system processes with memory, tools, and constrained authority over real machines. These are supposed to be the &amp;#039;semi-intelligent layer&amp;#039; between you and your homelab.

Volition has been running continuously in my personal infrastructure with multiple agents for more than a month now. However, this public release is new and has not yet been exercised end-to-end by external users. Expect rough edges in: setup and documentation flow, first-run ergonomics, and non-default configurations Core architecture and invariants are stable, but installation paths will be refined over the next few days as this release is tested in the open.

Related contents:

- [Episode 652: Have Your Bot Call My Bot @ Linux Unplugged](https://linuxunplugged.com/652).]]>
            </summary>
            <updated>2026-02-02T06:56:43+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11604</id>
            <title type="text"><![CDATA[Auto Claude]]></title>
            <link rel="alternate" href="https://github.com/AndyMik90/Auto-Claude" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11604"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Autonomous multi-agent coding framework that plans, builds, and validates software for you.

Related contents:

- [Faites de Claude une armée de développeurs à votre service @ Korben :fr:](https://korben.info/transformez-claude-en-une-armee-de-developpeurs-a-votre-service.html).]]>
            </summary>
            <updated>2026-01-26T08:43:31+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11580</id>
            <title type="text"><![CDATA[GitHub Copilot CLI SDKs]]></title>
            <link rel="alternate" href="https://github.com/github/copilot-sdk" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11580"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Multi-platform SDK for integrating GitHub Copilot Agent into apps and services.

Embed Copilot&amp;#039;s agentic workflows in your application—now available in Technical preview as a programmable SDK for Python, TypeScript, Go, and .NET.

The GitHub Copilot SDK exposes the same engine behind Copilot CLI: a production-tested agent runtime you can invoke programmatically. No need to build your own orchestration—you define agent behavior, Copilot handles planning, tool invocation, file edits, and more.

Related contents:

- [Build an agent into any app with the GitHub Copilot SDK @ GitHub Blog](https://github.blog/news-insights/company-news/build-an-agent-into-any-app-with-the-github-copilot-sdk/).]]>
            </summary>
            <updated>2026-01-23T12:42:41+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11559</id>
            <title type="text"><![CDATA[rtfmbro-mcp]]></title>
            <link rel="alternate" href="https://github.com/marckrenn/rtfmbro-mcp" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11559"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[rtfmbro provides always-up-to-date, version-specific package documentation as context for coding agents. An alternative to context7]]>
            </summary>
            <updated>2026-01-21T13:55:56+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11543</id>
            <title type="text"><![CDATA[Universal Commerce Protocol (UCP)]]></title>
            <link rel="alternate" href="https://ucp.dev/#" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11543"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The common language for platforms, agents and businesses.

UCP defines building blocks for agentic commerce—from discovering and buying to post purchase experiences—allowing the ecosystem to interoperate through one standard, without custom builds. 

- [Universal Commerce Protocol (UCP) @ GitHub](https://github.com/Universal-Commerce-Protocol/ucp).

Related contents:

- [Under the Hood: Universal Commerce Protocol (UCP) @ Google for Developers](https://developers.googleblog.com/under-the-hood-universal-commerce-protocol-ucp/).
- [Google lance un protocole qui va transformer l&amp;#039;achat en ligne, Carrefour fait partie des premiers à l&amp;#039;adopter @ Clubic :fr:](https://www.clubic.com/actualite-594658-google-lance-un-protocole-qui-va-transformer-l-achat-en-ligne-carrefour-fait-partie-des-premiers-a-l-adopter.html).]]>
            </summary>
            <updated>2026-01-20T09:20:59+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11534</id>
            <title type="text"><![CDATA[OpenWork]]></title>
            <link rel="alternate" href="https://openwork.software/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11534"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[An open-source alternative to Claude Cowork, powered by OpenCode.

OpenWork is an extensible, open-source “Claude Work” style system for knowledge workers.
It’s a native desktop app that runs OpenCode under the hood, but presents it as a clean, guided workflow.

- [OpenWork @ GitHub](https://github.com/different-ai/openwork).]]>
            </summary>
            <updated>2026-01-20T06:47:02+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11530</id>
            <title type="text"><![CDATA[MiroThinker]]></title>
            <link rel="alternate" href="https://dr.miromind.ai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11530"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[MiroThinker is an open source deep research agent optimized for research and prediction. It achieves a 60.2% Avg@8 score on the challenging GAIA benchmark. 

- [MiroThinker @ GitHub](https://github.com/MiroMindAI/MiroThinker).]]>
            </summary>
            <updated>2026-01-19T13:07:11+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11522</id>
            <title type="text"><![CDATA[Leash]]></title>
            <link rel="alternate" href="https://leash.strongdm.ai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11522"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Security, visibility, and authorization for AI agents

Leash wraps AI coding agents in containers and monitors their activity. You define policies in Cedar; Leash enforces them instantly.

Authorize and monitor your AI agents with policy enforcement, sandboxed execution, and real-time observability—ensuring they operate safely within your defined boundaries.

- [Leash @ GitHub](https://github.com/strongdm/leash).]]>
            </summary>
            <updated>2026-01-19T06:51:20+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11484</id>
            <title type="text"><![CDATA[Gambit]]></title>
            <link rel="alternate" href="https://github.com/bolt-foundry/gambit" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11484"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Agent harness framework for building, running, and verifying LLM workflows.

Gambit helps you build reliable LLM workflows by composing small, typed “decks”
with clear inputs/outputs and guardrails. Run decks locally, stream traces, and
debug with a built-in UI.]]>
            </summary>
            <updated>2026-01-16T13:03:01+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11483</id>
            <title type="text"><![CDATA[Oh My OpenCode]]></title>
            <link rel="alternate" href="https://github.com/code-yeongyu/oh-my-opencode" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11483"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The Best Agent Harness. Meet Sisyphus: The Batteries-Included Agent that codes like you.]]>
            </summary>
            <updated>2026-01-16T12:59:28+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11470</id>
            <title type="text"><![CDATA[Agent Skills]]></title>
            <link rel="alternate" href="https://agentskills.io/home" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11470"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A simple, open format for giving agents new capabilities and expertise.
Agent Skills are folders of instructions, scripts, and resources that agents can discover and use to do things more accurately and efficiently.

- [Agent Skills @ GitHub](https://github.com/agentskills/agentskills).

Related contents:

- [Vercel&amp;#039;s Agent Skills @ GitHub](https://github.com/vercel-labs/agent-skills).
- [MCP, Skills, and Agents @ cramr](https://cra.mr/mcp-skills-and-agents/).
- [Agent Skills vs. Rules vs. Commands @ builder.io](https://www.builder.io/blog/agent-skills-rules-commands).
- [3 Principles for Designing Agent Skills @ Block Engineering Blog](https://engineering.block.xyz/blog/3-principles-for-designing-agent-skills).
- [Claude Code Skills Are a Massive Security Threat — Greg Pstrucha, Sentry @ Mastra&amp;#039;s YouTube](https://www.youtube.com/watch?v=WNJHMoHTrBU).]]>
            </summary>
            <updated>2026-06-04T05:55:09+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11457</id>
            <title type="text"><![CDATA[mgrep]]></title>
            <link rel="alternate" href="https://www.mgrep.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11457"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Semantic search for agents.

 A calm, CLI-native way to semantically grep everything, like code, images, pdfs and more. 

- [mgrep @ GitHub](https://github.com/mixedbread-ai/mgrep).

Related contents:

- [Mgrep c&amp;#039;est quoi ? @ RayaneRachid&amp;#039;s X](https://nitter.net/RayaneRachid_/status/2008950450931048575).
- [\#161 - Veille tech et l&amp;#039;interview de Jessim @ Quoi de neuf les devs? :fr:](https://happytodev.substack.com/p/quoi-de-neuf-les-devs-161-veille).]]>
            </summary>
            <updated>2026-01-13T14:31:49+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11449</id>
            <title type="text"><![CDATA[Ralph]]></title>
            <link rel="alternate" href="https://github.com/snarktank/ralph" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11449"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Ralph is an autonomous AI agent loop that runs repeatedly until all PRD items are complete. 

Ralph is an autonomous AI agent loop that runs Amp repeatedly until all PRD items are complete. Each iteration is a fresh Amp instance with clean context. Memory persists via git history, progress.txt, and prd.json.

Related contents:

- [Ralph Wiggum as a &amp;quot;software engineer&amp;quot; @ Geoffrey Huntley](https://ghuntley.com/ralph/).
- [a brief history of ralph @ humanlayer](https://www.humanlayer.dev/blog/brief-history-of-ralph).]]>
            </summary>
            <updated>2026-01-20T13:16:18+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11447</id>
            <title type="text"><![CDATA[Kilo]]></title>
            <link rel="alternate" href="https://kilo.ai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11447"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Move at Kilo Speed.
Build, ship, and iterate faster with the most popular open source coding agent.

 Kilo is the all-in-one agentic engineering platform. Build, ship, and iterate faster with the most popular open source coding agent. #1 on OpenRouter. 750k+ Kilo Coders. 6.1 trillion tokens/month. 

- [Kilo @ GitHub](https://github.com/Kilo-Org/kilocode).

Related contents:

- [Episode \#672: From GitLab to Kilo Code @ Changelog Interviews](https://changelog.com/podcast/672).]]>
            </summary>
            <updated>2026-01-13T06:46:42+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11429</id>
            <title type="text"><![CDATA[Orla]]></title>
            <link rel="alternate" href="https://github.com/dorcha-inc/orla" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11429"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A dead-simple unix tool for lightweight open-source local agents.

Orla is a unix tool for running lightweight open-source agents. It is easy to add to a script, use with pipes, or build things on top of.

Related contents:

- [Orla - L&amp;#039;outil CLI qui transforme votre terminal en assistant IA local @ Korben :fr:](https://korben.info/orla-agent-ia-local-cli.html).]]>
            </summary>
            <updated>2026-01-12T08:19:04+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11422</id>
            <title type="text"><![CDATA[HolmesGPT]]></title>
            <link rel="alternate" href="https://holmesgpt.dev/latest/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11422"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[AI Agent for Troubleshooting Cloud-Native Environments.
Your 24/7 On-Call AI Agent - Solve Alerts Faster with Automatic Correlations, Investigations, and More.

HolmesGPT is an AI agent for investigating problems in your cloud, finding the root cause, and suggesting remediations. It has dozens of built-in integrations for cloud providers, observability tools, and on-call systems.

- [HolmesGPT @ GitHub](https://github.com/HolmesGPT/holmesgpt).

Related contents:

- [HolmesGPT: Agentic troubleshooting built for the cloud native era @ CNCF](https://www.cncf.io/blog/2026/01/07/holmesgpt-agentic-troubleshooting-built-for-the-cloud-native-era/).
- [Auto-diagnosing Kubernetes alerts with HolmesGPT and CNCF tools @ CNCF](https://www.cncf.io/blog/2026/04/21/auto-diagnosing-kubernetes-alerts-with-holmesgpt-and-cncf-tools/).]]>
            </summary>
            <updated>2026-04-22T12:47:27+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11414</id>
            <title type="text"><![CDATA[pi coding agent]]></title>
            <link rel="alternate" href="https://github.com/badlogic/pi-mono" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11414"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[AI agent toolkit: coding agent CLI, unified LLM API, TUI &amp;amp; web UI libraries, Slack bot, vLLM pods.]]>
            </summary>
            <updated>2026-01-07T13:36:13+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11413</id>
            <title type="text"><![CDATA[Mantic.sh]]></title>
            <link rel="alternate" href="https://github.com/marcoaapfortes/Mantic.sh" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11413"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A structural code search engine for AI agents. Provides sub-500ms file ranking across massive codebases without embeddings, vector databases, or external dependencies.

Mantic is an infrastructure layer designed to remove unnecessary context retrieval overhead for AI agents. It infers intent from file structure and metadata rather than brute-force reading content, enabling retrieval speeds faster than human reaction time.]]>
            </summary>
            <updated>2026-01-07T13:27:30+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11376</id>
            <title type="text"><![CDATA[Awesome Agentic Patterns]]></title>
            <link rel="alternate" href="https://agentic-patterns.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11376"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A curated catalogue of agentic AI patterns — real‑world tricks, workflows, and mini‑architectures that help autonomous or semi‑autonomous AI agents get useful work done in production.

- [Awesome Agentic Patterns @ GitHub](https://github.com/nibzard/awesome-agentic-patterns).

Related contents:

- [Looper: The AI Junior That Never Forgets the Backlog @ Nikola Balic](https://www.nibzard.com/looper-article/).]]>
            </summary>
            <updated>2026-01-20T13:09:11+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11374</id>
            <title type="text"><![CDATA[React Grab]]></title>
            <link rel="alternate" href="https://www.react-grab.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11374"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Select context for coding agents directly from your website.

How? Point at any element and press ⌘C (Mac) or Ctrl+C (Windows/Linux) to copy the file name, React component, and HTML source code.

It makes tools like Cursor, Claude Code, Copilot run up to 3× faster and more accurate.

- [React Grab @ GitHub](https://github.com/aidenybai/react-grab).]]>
            </summary>
            <updated>2026-01-05T12:52:43+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11356</id>
            <title type="text"><![CDATA[Gas Town]]></title>
            <link rel="alternate" href="https://github.com/steveyegge/gastown" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11356"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Multi-agent orchestrator for Claude Code. Track work with convoys; sling to agents.

Related contents:

- [Welcome to Gas Town @ Steve Yegge&amp;#039;s Medium](https://steve-yegge.medium.com/welcome-to-gas-town-4f25ee16dd04).
- [Gas Town Decoded @ Andrew Lilley Brinker](https://www.alilleybrinker.com/mini/gas-town-decoded/).
- [How to think about Gas Town @ Steve Klabnik](https://steveklabnik.com/writing/how-to-think-about-gas-town/).
- [Agent Psychosis: Are We Going Insane? @ Armin Ronacher&amp;#039;s Thoughts and Writings](https://lucumr.pocoo.org/2026/1/18/agent-psychosis/).
- [Gas Town’s Agent Patterns, Design Bottlenecks, and Vibecoding at Scale @ Maggie Appleton](https://maggieappleton.com/gastown/).
- [Move Over Gas Town, Claude Has First-Party Agent Orchestration @ Andrew Lilley Brinker](https://www.alilleybrinker.com/mini/move-over-gas-town/).]]>
            </summary>
            <updated>2026-02-06T14:19:31+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11351</id>
            <title type="text"><![CDATA[Worktrunk]]></title>
            <link rel="alternate" href="https://worktrunk.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11351"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows.

Worktrunk&amp;#039;s three core commands make worktrees as easy as branches. Plus, Worktrunk has a bunch of quality-of-life features to simplify working with many parallel changes, including hooks to automate local workflows.

- [Worktrunk @ GitHub](https://github.com/max-sixty/worktrunk).]]>
            </summary>
            <updated>2026-01-05T06:51:57+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11346</id>
            <title type="text"><![CDATA[PentestAgent]]></title>
            <link rel="alternate" href="https://github.com/GH05TCREW/pentestagent" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11346"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[AI Penetration Testing.

PentestAgent is an AI agent framework for black-box security testing, supporting bug bounty, red-team, and penetration testing workflows.]]>
            </summary>
            <updated>2025-12-31T07:54:16+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11325</id>
            <title type="text"><![CDATA[Word GPT Plus]]></title>
            <link rel="alternate" href="https://github.com/Kuingsmile/word-GPT-Plus?" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11325"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Word GPT Plus is a word add-in which integrates the AI&amp;amp;Agent into Microsoft Word. 

Word GPT Plus seamlessly integrates AI and Agent directly into Microsoft Word, allowing you to generate, translate, summarize, and polish text directly within your documents. Enhance your writing workflow without leaving your Word environment.]]>
            </summary>
            <updated>2025-12-29T08:41:40+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11313</id>
            <title type="text"><![CDATA[Vibium]]></title>
            <link rel="alternate" href="https://vibium.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11313"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Browser automation without the drama.
 Browser automation for AI agents and humans.

Vibium is browser automation infrastructure built for AI agents. A single binary handles browser lifecycle, WebDriver BiDi protocol, and exposes an MCP server — so Claude Code (or any MCP client) can drive a browser with zero setup. Works great for AI agents, test automation, and anything else that needs a browser.

- [Vibium @ GitHub](https://github.com/VibiumDev/vibium).]]>
            </summary>
            <updated>2025-12-29T07:30:28+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11310</id>
            <title type="text"><![CDATA[HelixML]]></title>
            <link rel="alternate" href="https://helix.ml/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11310"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[AI Agents on a Private GenAI Stack.

 ♾️ Helix is a private GenAI stack for building AI agents with declarative pipelines, knowledge (RAG), API bindings, and first-class testing. 

- [HelixML @ GitHub](https://github.com/helixml/helix).

Related contents:

- [We Mass-Deployed 15-Year-Old Screen Sharing Technology and It&amp;#039;s Actually Better @ HelixML](https://blog.helix.ml/p/we-mass-deployed-15-year-old-screen).]]>
            </summary>
            <updated>2025-12-24T12:44:57+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11282</id>
            <title type="text"><![CDATA[OpenMemory]]></title>
            <link rel="alternate" href="https://openmemory.cavira.app/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11282"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Long-term Memory for AI Agents.

 Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc. 

- [OpenMemory @ GitHub](https://github.com/CaviraOSS/OpenMemory).]]>
            </summary>
            <updated>2025-12-23T08:52:55+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11279</id>
            <title type="text"><![CDATA[Destructive Git Command Protection for Claude Code]]></title>
            <link rel="alternate" href="https://github.com/Dicklesworthstone/misc_coding_agent_tips_and_scripts/blob/main/DESTRUCTIVE_GIT_COMMAND_CLAUDE_HOOKS_SETUP.md" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11279"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[On December 17, 2025, an AI agent (Claude) ran git checkout -- on multiple files containing hours of uncommitted work from another agent (Codex). This destroyed the work instantly and silently. The files were eventually recovered from a dangling Git object, but this incident revealed a critical gap: AI agents can execute destructive commands without understanding the consequences.

The AGENTS.md file already forbade such commands, but instructions alone don&amp;#039;t prevent execution. This hook provides mechanical enforcement - the command is blocked before it can run.]]>
            </summary>
            <updated>2025-12-22T13:18:44+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11273</id>
            <title type="text"><![CDATA[SkillsMP]]></title>
            <link rel="alternate" href="https://skillsmp.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11273"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Agent Skills Marketplace -  Claude, Codex &amp;amp; ChatGPT Skills.

Related contents:

- [SkillsMP - Plus de 26 000 skills Claude à portée de clic @ Korben n :fr:](https://korben.info/skillsmp-marketplace-skills-claude-code-github.html).]]>
            </summary>
            <updated>2025-12-22T08:29:27+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11266</id>
            <title type="text"><![CDATA[Kimi CLI]]></title>
            <link rel="alternate" href="https://github.com/MoonshotAI/kimi-cli" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11266"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Kimi CLI is a new CLI agent that can help you with your software development tasks and terminal operations.]]>
            </summary>
            <updated>2025-12-17T13:03:38+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11215</id>
            <title type="text"><![CDATA[Layrr]]></title>
            <link rel="alternate" href="https://www.layrr.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11215"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Layrr is the visual editor for real code.
Design visually, edit any stack, own everything. 
 A browser coding agent interface for selecting elements and sending instructions directly to Claude Code. 

- [Layrr @ GitHub](https://github.com/thetronjohnson/layrr).]]>
            </summary>
            <updated>2025-12-12T07:29:23+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11214</id>
            <title type="text"><![CDATA[SwiftMCP]]></title>
            <link rel="alternate" href="https://github.com/Cocoanetics/SwiftMCP" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11214"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Model Context Protocol Server for Swift.

A Swift implementation of the MCP (Model Context Protocol) for JSON-RPC over various transports.]]>
            </summary>
            <updated>2025-12-12T07:27:51+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11201</id>
            <title type="text"><![CDATA[Agent-lightning]]></title>
            <link rel="alternate" href="https://microsoft.github.io/agent-lightning/stable/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11201"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Agent Lightning is the absolute trainer to light up AI agents.

agent-lightning is an open-source framework for training and optimizing AI agents—enabling reinforcement learning (RL), automatic prompt optimization, supervised fine-tuning, and more—without requiring substantial changes to existing agent code. It works with virtually any agent framework (e.g., LangChain, OpenAI Agents SDK, and AutoGen) and provides modular components to collect agent execution data and iteratively improve agent performance via a decoupled RL training loop.

- [Agent Lightning @ GitHub](https://github.com/microsoft/agent-lightning).]]>
            </summary>
            <updated>2026-01-21T13:03:08+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11187</id>
            <title type="text"><![CDATA[Steer]]></title>
            <link rel="alternate" href="https://github.com/imtt-dev/steer" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11187"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The Active Reliability Layer for AI Agents. Catch failures, teach fixes, and automate reliability.

Steer is an open-source Python library that intercepts agent failures (hallucinations, bad JSON, PII leaks) and allows you to inject fixes via a local dashboard without changing your code.

Related contents:

- [The &amp;quot;Confident Idiot&amp;quot; Problem: Why AI Needs Hard Rules, Not Vibe Checks @ Steer labs&amp;#039; SubStack](https://steerlabs.substack.com/p/confident-idiot-problem).]]>
            </summary>
            <updated>2025-12-09T07:10:24+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11175</id>
            <title type="text"><![CDATA[🍎📚 Cupertino]]></title>
            <link rel="alternate" href="https://github.com/mihaelamj/cupertino" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11175"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A local Apple Documentation crawler and MCP server. Written in Swift.

A Swift-based tool to crawl, index, and serve Apple&amp;#039;s developer documentation to AI agents via the Model Context Protocol (MCP).

Related contents:

- [Cupertino: Offline Apple Documentation for AI Agents @ Aleahim.com](https://aleahim.com/blog/cupertino/).
- [Cupertino - Plus de code iOS pourri avec vos assistants IA @ Korben :fr:](https://korben.info/cupertino-mcp-claude-code-documentation-apple.html).]]>
            </summary>
            <updated>2025-12-08T11:33:41+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11101</id>
            <title type="text"><![CDATA[Hugging Face Agents Course]]></title>
            <link rel="alternate" href="https://huggingface.co/agents-course" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11101"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[This interactive, certified course will guide you through building and deploying your own AI Agents.]]>
            </summary>
            <updated>2025-11-25T08:01:45+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11084</id>
            <title type="text"><![CDATA[mux]]></title>
            <link rel="alternate" href="https://cmux.io/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11084"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A desktop app for isolated, parallel agentic development.

mux (Coding Agent Multiplexer) is a cross-platform desktop application for AI-assisted development with isolated workspace management.

- [mux @ GitHub](https://github.com/coder/mux).]]>
            </summary>
            <updated>2025-11-24T12:53:46+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11076</id>
            <title type="text"><![CDATA[🛠️ kit]]></title>
            <link rel="alternate" href="https://kit.cased.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11076"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The toolkit for AI devtools context engineering. Build with codebase mapping, symbol extraction, and many kinds of code search. 

kit is a production-ready toolkit for codebase mapping, symbol extraction, code search, and building LLM-powered developer tools, agents, and workflows.

kit shines for getting precise, accurate, and relevant context to LLMs. Use kit to build code reviewers, code generators and graphs, even full-fledged coding assistants: all enriched with the right code context.

- [kit 🛠️ Code Intelligence Toolkit @ GitHub](https://github.com/cased/kit?utm_source=tldrnewsletter)]]>
            </summary>
            <updated>2025-11-24T12:16:26+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11037</id>
            <title type="text"><![CDATA[OpenSpec]]></title>
            <link rel="alternate" href="https://openspec.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11037"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A lightweight spec‑driven framework.

OpenSpec aligns humans and AI coding assistants with spec-driven development so you agree on what to build before any code is written. No API keys required.

- [OpenSpec @ GitHub](https://github.com/Fission-AI/OpenSpec).

Related contents:

- [Spec-driven development doesn&amp;#039;t work if you&amp;#039;re too confused to write the spec @ deontologician](https://publish.obsidian.md/deontologician/Posts/Spec-driven+development+doesn&amp;#039;t+work+if+you&amp;#039;re+too+confused+to+write+the+spec).
- [The uncomfortable truth about vibe coding @ RedHat Developer](https://developers.redhat.com/articles/2026/02/17/uncomfortable-truth-about-vibe-coding).
- [What spec-driven development gets wrong @ augment code](https://www.augmentcode.com/blog/what-spec-driven-development-gets-wrong).]]>
            </summary>
            <updated>2026-02-24T07:52:44+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11032</id>
            <title type="text"><![CDATA[Skyvern]]></title>
            <link rel="alternate" href="https://www.skyvern.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11032"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[AI Browser Automation.
 Automate browser based workflows with AI.

Skyvern automates browser-based workflows using LLMs and computer vision. It provides a simple API endpoint to fully automate manual workflows on a large number of websites, replacing brittle or unreliable automation solutions.

- [Skyvern @ GitHub](https://github.com/Skyvern-AI/skyvern).]]>
            </summary>
            <updated>2025-11-21T12:42:51+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11019</id>
            <title type="text"><![CDATA[emdash]]></title>
            <link rel="alternate" href="https://emdash.sh/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11019"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Emdash is an orchestration layer for running multiple coding agents in parallel in isolated Git worktrees.

An orchestration layer for running multiple coding agents in parallel, each isolated in its own Git worktree. Run several agent instances concurrently to tackle independent subtasks or experiments.

Emdash lets you develop and test multiple features with multiple agents in parallel. It’s provider-agnostic (we support 10+ CLIs, such as Claude Code and Codex) and runs each agent in its own Git worktree to keep changes clean; when the environment matters, you can run a PR in its own Docker container. Hand off Linear, GitHub, or Jira tickets to an agent, review diffs side-by-side, and keep everything local.

- [emdash @ GitHub](https://github.com/generalaction/emdash).]]>
            </summary>
            <updated>2026-02-25T12:42:23+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10853</id>
            <title type="text"><![CDATA[Pipelex]]></title>
            <link rel="alternate" href="https://www.pipelex.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10853"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[AI Workflows That Agents Build &amp;amp; Run.
Open Language for Agents to Build AI Workflows.

The open standard devtool for repeatable AI workflows.
Write business logic, not API calls.

- [Pipelex @ GitHub](https://github.com/pipelex/pipelex).]]>
            </summary>
            <updated>2025-11-03T13:00:33+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10838</id>
            <title type="text"><![CDATA[cmux]]></title>
            <link rel="alternate" href="https://www.cmux.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10838"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Universal AI coding agent manager for 10x engineers.

 cmux lets you run Claude Code, Codex CLI, Amp, Gemini CLI, Cursor CLI, Opencode, and other coding agent CLIs in parallel across multiple tasks 

- [cmux @ GitHub](https://github.com/manaflow-ai/cmux).]]>
            </summary>
            <updated>2025-10-31T11:40:21+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10812</id>
            <title type="text"><![CDATA[Tavily]]></title>
            <link rel="alternate" href="https://www.tavily.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10812"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The Web Access Layer for AI Agents.

Connect Your Agent to the Web. Powering the Internet of Agents with fast, secure and reliable web access APIs.

Related contents:

- [RAG Against The Machine @ Quoi de neuf les devs ? :fr:](https://happytodev.substack.com/p/quoi-de-neuf-les-devs-153-veille?open=false#%C2%A7rag-against-the-machine).]]>
            </summary>
            <updated>2025-10-29T16:23:15+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10811</id>
            <title type="text"><![CDATA[Dexto]]></title>
            <link rel="alternate" href="https://www.dexto.ai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10811"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The Intelligence Engine. Turn Natural Language Into Action.
 The Intelligence Layer for AI agents. Connect your models, tools, and data to create agentic apps that can think, act and talk to you. 

An all-in-one toolkit to build agentic applications that turn natural language into real-world actions.

Want to build AI-native apps that respond to natural language? Dexto is the intelligence layer that makes it easy to build agentic apps like AI assistants and copilots. Describe your agents, plug in your tools, and watch them respond to plain English.

- [Dexto @ GitHub](https://github.com/truffle-ai/dexto).]]>
            </summary>
            <updated>2025-10-29T12:59:44+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10782</id>
            <title type="text"><![CDATA[Peekaboo]]></title>
            <link rel="alternate" href="https://www.peekaboo.boo/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10782"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[AI Vision for macOS. Fast Screen Capture &amp;amp; VQA.

Peekaboo is a macOS CLI &amp;amp; optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models. 

- [Peekaboo @ GitHub](https://github.com/steipete/Peekaboo).

Related contents:

- [Accelerate developer productivity with these 9 open source AI and MCP projects @ GitHub blog](https://github.blog/open-source/accelerate-developer-productivity-with-these-9-open-source-ai-and-mcp-projects/).]]>
            </summary>
            <updated>2025-10-27T14:08:36+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10781</id>
            <title type="text"><![CDATA[nuxt-mcp / vite-plugin-mcp]]></title>
            <link rel="alternate" href="https://github.com/antfu/nuxt-mcp" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10781"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[MCP server helping models to understand your Vite/Nuxt app better. 

Related contents:

- [Accelerate developer productivity with these 9 open source AI and MCP projects @ GitHub blog](https://github.blog/open-source/accelerate-developer-productivity-with-these-9-open-source-ai-and-mcp-projects/).]]>
            </summary>
            <updated>2025-10-27T14:06:14+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10780</id>
            <title type="text"><![CDATA[FastAPI MCP]]></title>
            <link rel="alternate" href="https://fastapi-mcp.tadata.com/getting-started/welcome" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10780"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!

MCP (Model Context Protocol) is the emerging standard to define how AI agents communicate with applications. Using FastAPI-MCP, creating a secured MCP server to your application takes only 3 lines of code.

- [FastAPI MCP @ GitHub](https://github.com/tadata-org/fastapi_mcp).

Related contents:

- [Accelerate developer productivity with these 9 open source AI and MCP projects @ GitHub blog](https://github.blog/open-source/accelerate-developer-productivity-with-these-9-open-source-ai-and-mcp-projects/).]]>
            </summary>
            <updated>2025-10-27T14:04:59+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10779</id>
            <title type="text"><![CDATA[n8n MCP]]></title>
            <link rel="alternate" href="https://www.n8n-mcp.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10779"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[AI-Powered n8n Workflow Automation.

Model Context Protocol server enabling AI assistants to build accurate n8n workflows.
Access 525+ n8n nodes with 99% property coverage. Reduce configuration errors and speed up workflow creation.

- [n8n MCP @ GitHub](https://github.com/czlonkowski/n8n-mcp).

Related contents:

- [Accelerate developer productivity with these 9 open source AI and MCP projects @ GitHub blog](https://github.blog/open-source/accelerate-developer-productivity-with-these-9-open-source-ai-and-mcp-projects/).
- [n8n MCP - Quand votre IA pilote vos workflows @ Korben :fr:](https://korben.info/n8n-mcp-serveur-ia-automatisation.html).]]>
            </summary>
            <updated>2026-03-16T09:57:04+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10770</id>
            <title type="text"><![CDATA[React Grab]]></title>
            <link rel="alternate" href="https://react-grab.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10770"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Grab any element on in your app and give it to Cursor, Claude Code, etc.

By default coding agents cannot access elements on your page. React Grab fixes this - just point and click to provide context!

- [React Grab @ GitHub](https://github.com/aidenybai/react-grab).]]>
            </summary>
            <updated>2025-10-27T11:28:32+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10744</id>
            <title type="text"><![CDATA[Dexter 🤖]]></title>
            <link rel="alternate" href="https://github.com/virattt/dexter" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10744"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[An autonomous agent for deep financial research.

Dexter is an autonomous financial research agent that thinks, plans, and learns as it works. It performs analysis using task planning, self-reflection, and real-time market data. Think Claude Code, but built specifically for financial research.]]>
            </summary>
            <updated>2025-10-21T05:59:11+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10741</id>
            <title type="text"><![CDATA[AGNTCY]]></title>
            <link rel="alternate" href="https://agntcy.org/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10741"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Building infrastructure for the Internet of Agents.

The AGNTCY project provides the complete infrastructure stack for agent collaboration—discovery, identity, messaging, and observability that works across any vendor or framework. It is the foundational layer that lets specialized agents find each other, verify capabilities, and work together on complex problems.

- [AGNTCY Identity @ GitHub](https://github.com/agntcy/identity).
- [Agent Directory Protocol @ GitHub](https://github.com/agntcy/dir-spec).]]>
            </summary>
            <updated>2025-10-21T05:42:06+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10738</id>
            <title type="text"><![CDATA[⭐ Azure DevOps MCP Server]]></title>
            <link rel="alternate" href="https://github.com/microsoft/azure-devops-mcp" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10738"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The MCP server for Azure DevOps, bringing the power of Azure DevOps directly to your agents. 

Related contents:

- [Azure DevOps local MCP Server is generally available @ Microsoft Azure DevOps Blog](https://devblogs.microsoft.com/devops/azure-devops-local-mcp-server-generally-available/).]]>
            </summary>
            <updated>2025-10-20T12:18:05+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10706</id>
            <title type="text"><![CDATA[Inkeep]]></title>
            <link rel="alternate" href="https://inkeep.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10706"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[AI Agents that get real work done.

Ship Agent-powered assistants and automations that help your customers and 10x your teams.

 Create AI Agents in a No-Code Visual Builder or TypeScript SDK with full 2-way sync. For shipping AI assistants and multi-agent AI workflows. 

- [Inkeep documentation](https://docs.inkeep.com/overview).
- [Inkeep Agents @ GitHub](https://github.com/inkeep/agents).]]>
            </summary>
            <updated>2025-10-17T13:20:18+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10653</id>
            <title type="text"><![CDATA[Amplifier]]></title>
            <link rel="alternate" href="https://github.com/microsoft/amplifier" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10653"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Supercharged AI Development Environment.

Amplifier is a coordinated and accelerated development system that provides specialized AI agents, persistent knowledge that compounds over time, and workflows that execute complex methodologies.]]>
            </summary>
            <updated>2025-10-14T11:52:06+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10641</id>
            <title type="text"><![CDATA[Beads]]></title>
            <link rel="alternate" href="https://github.com/steveyegge/beads" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10641"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A memory upgrade for your coding agent.

Beads is a lightweight memory system for coding agents, using a graph-based issue tracker. Four kinds of dependencies work to chain your issues together like beads, making them easy for agents to follow for long distances, and reliably perform complex task streams in the right order.

Related contents:

- [Introducing Beads: A coding agent memory system @ Steve Yegge&amp;#039;s Medium](https://steve-yegge.medium.com/introducing-beads-a-coding-agent-memory-system-637d7d92514a).
- [Working with AI: How does it Know? @ Jessitron](https://jessitron.com/2026/01/10/ai-coding-trick-ask-it-how-it-knows/).
- [Agent Psychosis: Are We Going Insane? @ Armin Ronacher&amp;#039;s Thoughts and Writings](https://lucumr.pocoo.org/2026/1/18/agent-psychosis/).
- [Pi: The Minimal Agent Within OpenClaw @ Armin Ronacher&amp;#039;s Thoughts and Writings](https://lucumr.pocoo.org/2026/1/31/pi/).]]>
            </summary>
            <updated>2026-02-23T13:04:12+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10637</id>
            <title type="text"><![CDATA[EdgeAI for Beginners]]></title>
            <link rel="alternate" href="https://github.com/microsoft/edgeai-for-beginners" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10637"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[This course is designed to guide beginners through the exciting world of Edge AI, covering fundamental concepts, popular models, inference techniques, device-specific applications, model optimization, and the development of intelligent Edge AI agents.]]>
            </summary>
            <updated>2025-10-13T11:44:03+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10629</id>
            <title type="text"><![CDATA[cagent]]></title>
            <link rel="alternate" href="https://github.com/docker/cagent" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10629"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Agent Builder and Runtime by Docker Engineering.

cagent lets you create and run intelligent AI agents, where each agent has specialized knowledge, tools, and capabilities.
Think of it as allowing you to quickly build, share and run a team of virtual experts that collaborate to solve complex problems for you.

A powerful, easy to use, customizable multi-agent runtime that orchestrates AI agents with specialized capabilities and tools, and the interactions between agents.

Related contents:

- [Terraforming With AI @  Zachary Loeber&amp;#039;s dev.to](https://dev.to/zloeber/terraforming-with-ai-g0o).
- [Using MCP Servers: From Quick Tools to Multi-Agent Systems @ Docker Blog](https://www.docker.com/blog/mcp-servers-docker-toolkit-cagent-gateway/).]]>
            </summary>
            <updated>2026-01-26T12:51:17+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10589</id>
            <title type="text"><![CDATA[FleetCode]]></title>
            <link rel="alternate" href="https://github.com/built-by-as/FleetCode" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10589"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Light-weight control pane to run CLI coding agents(Claude Code, Codex) in parallel.

A desktop terminal application for running multiple CLI coding agents simultaneously, each in isolated git worktrees.]]>
            </summary>
            <updated>2025-10-10T13:44:04+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10552</id>
            <title type="text"><![CDATA[Jules]]></title>
            <link rel="alternate" href="https://jules.google/docs/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10552"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Jules is an experimental coding agent that helps you fix bugs, add documentation, and build new features. It integrates with GitHub, understands your codebase, and works asynchronously — so you can move on while it handles the task.

Related contents:

- [Introducing the Jules API @ Jules documentation](https://jules.google/docs/changelog/).]]>
            </summary>
            <updated>2025-10-06T11:48:06+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10497</id>
            <title type="text"><![CDATA[MCP PHP SDK]]></title>
            <link rel="alternate" href="https://github.com/modelcontextprotocol/php-sdk" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10497"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The official PHP SDK for Model Context Protocol servers and clients. Maintained in collaboration with The PHP Foundation.

Related contents:

- [PHP MCP Server SDK @ GitHub](https://github.com/php-mcp/server).
- [Symfony&amp;#039;s Model Context Protocol PHP SDK](https://github.com/symfony/mcp-sdk).
- [Announcing the Official PHP SDK for MCP @ The PHP Foundation](https://thephp.foundation/blog/2025/09/05/php-mcp-sdk/).
- [\#119: Les news sur le développement web et l&amp;#039;IA pour septembre 2025 RC2 @ Double Slash :fr:](https://double-slash.dev/podcasts/news-sept25-rc2/).]]>
            </summary>
            <updated>2025-10-02T06:15:13+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10495</id>
            <title type="text"><![CDATA[ai.robots.txt]]></title>
            <link rel="alternate" href="https://github.com/ai-robots-txt/ai.robots.txt" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10495"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A list of AI agents and robots to block. 

This list contains AI-related crawlers of all types, regardless of purpose. We encourage you to contribute to and implement this list on your own site. See information about the listed crawlers and the FAQ.

Related contents:

- [\#119: Les news sur le développement web et l&amp;#039;IA pour septembre 2025 RC2 @ Double Slash :fr:](https://double-slash.dev/podcasts/news-sept25-rc2/).
- [Comment bloquer les crawlers IA qui pillent votre site sans vous demander la permission ? @ Korben :fr:](https://korben.info/bloquer-crawlers-ia-robots-txt-htaccess-nginx.html).]]>
            </summary>
            <updated>2025-12-16T10:41:09+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10492</id>
            <title type="text"><![CDATA[Browser Echo MCP]]></title>
            <link rel="alternate" href="https://github.com/instructa/browser-echo" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10492"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[⚡ Stream browser logs to terminal, zero setup, perfect for Ai Agents. 

browser-echo makes it easy for you to read client-side logs directly in your coding agent during development.

Related contents:

- [\#118 - Les news sur le développement web et l&amp;#039;IA pour septembre 2025 RC1 @ Double Slash :fr:](https://double-slash.dev/podcasts/sept25-rc1/).]]>
            </summary>
            <updated>2025-10-02T05:54:23+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10489</id>
            <title type="text"><![CDATA[Laravel Boost]]></title>
            <link rel="alternate" href="https://boost.laravel.com/installed" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10489"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Laravel Boost accelerates AI-assisted development by providing the essential context and structure that AI needs to generate high-quality, Laravel-specific code.

- [Laravel Boost @ GitHub](https://github.com/laravel/boost).

Related contents:

- [Getting Started with Laravel Boost @ Laravel&amp;#039;s YouTube](https://www.youtube.com/watch?v=sUtRcpma8iU).
- [\#118 - Les news sur le développement web et l&amp;#039;IA pour septembre 2025 RC1 @ Double Slash :fr:](https://double-slash.dev/podcasts/sept25-rc1/).]]>
            </summary>
            <updated>2025-10-02T05:47:27+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10458</id>
            <title type="text"><![CDATA[Chrome DevTools MCP]]></title>
            <link rel="alternate" href="https://github.com/chromeDevTools/chrome-devtools-mcp/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10458"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[chrome-devtools-mcp lets your coding agent (such as Gemini, Claude, Cursor or Copilot) control and inspect a live Chrome browser. It acts as a Model-Context-Protocol (MCP) server, giving your AI coding assistant access to the full power of Chrome DevTools for reliable automation, in-depth debugging, and performance analysis.

Related contents:

- [Give your AI eyes: Introducing Chrome DevTools MCP @ Addy Osmani](https://addyosmani.com/blog/devtools-mcp/).]]>
            </summary>
            <updated>2025-09-30T05:37:16+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10448</id>
            <title type="text"><![CDATA[Cloudflare Agents]]></title>
            <link rel="alternate" href="https://developers.cloudflare.com/agents/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10448"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The Agents SDK enables you to build and deploy AI-powered agents that can autonomously perform tasks, communicate with clients in real time, call AI models, persist state, schedule tasks, run asynchronous workflows, browse the web, query data from your database, support human-in-the-loop interactions, and a lot more.

- [Cloudflare Agents @ GitHub](https://github.com/cloudflare/agents).

Related contents:

- [Code Mode: the better way to use MCP @ Cloudflare blog](https://blog.cloudflare.com/code-mode/).]]>
            </summary>
            <updated>2025-09-29T12:20:33+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10421</id>
            <title type="text"><![CDATA[HexStrike AI]]></title>
            <link rel="alternate" href="https://www.hexstrike.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10421"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Revolutionary AI-Powered Offensive Security Framework.

 HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly bridge LLMs with real-world offensive security capabilities. 

- [HexStrike AI MCP Agents v6.0 @ GitHub](https://github.com/0x4m4/hexstrike-ai).]]>
            </summary>
            <updated>2025-09-29T05:46:52+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10385</id>
            <title type="text"><![CDATA[Tessl]]></title>
            <link rel="alternate" href="https://tessl.io/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10385"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[AI Native Development Platform.

Supercharge your agents with spec-driven development.
Get the speed of agentic coding with the reliability of production software.

Related contents:

- [Ep 63: Running Linux on an IPad @ Linux Matters](https://linuxmatters.sh/63/).
- [The uncomfortable truth about vibe coding @ RedHat Developer](https://developers.redhat.com/articles/2026/02/17/uncomfortable-truth-about-vibe-coding).]]>
            </summary>
            <updated>2026-02-24T07:19:15+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10377</id>
            <title type="text"><![CDATA[Active Agent]]></title>
            <link rel="alternate" href="https://www.activeagents.ai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10377"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The AI Framework For Ruby on Rails. Rails framework for Agent Apps.

Active Agent is a free open source framework that lets ANY Rails dev ship real, user-facing AI features using controllers, views, &amp;amp; background jobs.

Active Agent provides that missing AI layer in the Rails framework, offering a structured approach to building AI-powered applications through Agent Oriented Programming. Now Agents are Controllers! Designing applications using agents allows developers to create modular, reusable components that can be easily integrated into existing systems. This approach promotes code reusability, maintainability, and scalability, making it easier to build complex AI-driven applications with the Object Oriented Ruby code you already use today.

- [ActiveAgent @ GitHub](https://github.com/activeagents/activeagent).

Related contents:

- [Exploring Active Agent, or can we build AI features the Rails way? @ Evil Martians](https://evilmartians.com/chronicles/exploring-active-agent-or-can-we-build-ai-features-the-rails-way).]]>
            </summary>
            <updated>2025-09-24T12:50:34+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10365</id>
            <title type="text"><![CDATA[OpenPoke]]></title>
            <link rel="alternate" href="https://github.com/shlokkhemani/openpoke" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10365"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[OpenPoke is a simplified, open-source take on Interaction Company’s Poke assistant—built to show how a multi-agent orchestration stack can feel genuinely useful. It keeps the handful of things Poke is great at (email triage, reminders, and persistent agents) while staying easy to spin up locally.

Related contents:

- [OpenPoke: Recreating Poke&amp;#039;s Architecture @ Shlok Khemani](https://www.shloked.com/writing/openpoke).]]>
            </summary>
            <updated>2025-09-23T11:27:54+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10303</id>
            <title type="text"><![CDATA[Codebuff]]></title>
            <link rel="alternate" href="https://www.codebuff.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10303"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Generate code from the terminal! 
Supercharge Your AI Coding.
Simple. Fast. Powerful. Codebuff works in your terminal.

Codebuff is an open-source AI coding assistant that edits your codebase through natural language instructions. Instead of using one model for everything, it coordinates specialized agents that work together to understand your project and make precise changes.

- [Codebuff @ GitHub](https://github.com/CodebuffAI/codebuff).]]>
            </summary>
            <updated>2025-09-19T11:49:48+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10293</id>
            <title type="text"><![CDATA[Terragon]]></title>
            <link rel="alternate" href="https://www.terragonlabs.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10293"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Background Agents for Claude Code.

Terragon is a developer platform that lets you run AI coding agents in the cloud. Whether you&amp;#039;re at your browser, in your terminal, or on your phone, Terragon works wherever you are. Offload coding tasks and come back to pull requests ready to review.]]>
            </summary>
            <updated>2025-09-19T06:06:40+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10292</id>
            <title type="text"><![CDATA[Open SWE]]></title>
            <link rel="alternate" href="https://swe.langchain.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10292"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[An Open-Source Asynchronous Coding Agent.

Open SWE is an open-source cloud-based asynchronous coding agent built with LangGraph. It autonomously understands codebases, plans solutions, and executes code changes across entire repositories—from initial planning to opening pull requests.

- [Open SWE @ GitHub](https://github.com/langchain-ai/open-swe).]]>
            </summary>
            <updated>2025-09-19T06:05:42+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10290</id>
            <title type="text"><![CDATA[repomirror]]></title>
            <link rel="alternate" href="https://github.com/repomirrorhq/repomirror" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10290"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A tool to perform transformations on code repositories with AI. 

Related contents:

- [We Put a Coding Agent in a While Loop and It Shipped 6 Repos Overnight @ repomirror&amp;#039;s GitHub](https://github.com/repomirrorhq/repomirror/blob/main/repomirror.md).]]>
            </summary>
            <updated>2025-09-19T06:01:33+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10274</id>
            <title type="text"><![CDATA[AgentScope]]></title>
            <link rel="alternate" href="https://agentscope.io/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10274"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Agent-Oriented Programming for Building LLM Applications.

- [AgentScope’s documentation](https://doc.agentscope.io/).
- [AgentScope @ GitHub](https://github.com/agentscope-ai/agentscope).]]>
            </summary>
            <updated>2025-09-18T13:51:21+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10271</id>
            <title type="text"><![CDATA[MCP Registry]]></title>
            <link rel="alternate" href="https://github.com/mcp" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10271"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Servers and tools from the community that connect models to files, APIs, databases, and more.

Related contents:

- [Meet the GitHub MCP Registry: The fastest way to discover MCP Servers @ GitHub Blog](https://github.blog/ai-and-ml/github-copilot/meet-the-github-mcp-registry-the-fastest-way-to-discover-mcp-servers/).
- [How to find, install, and manage MCP servers with the GitHub MCP Registry @ GitHub Blog](https://github.blog/ai-and-ml/generative-ai/how-to-find-install-and-manage-mcp-servers-with-the-github-mcp-registry/).]]>
            </summary>
            <updated>2025-10-29T13:12:19+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10254</id>
            <title type="text"><![CDATA[Coze Studio]]></title>
            <link rel="alternate" href="https://github.com/coze-dev/coze-studio?utm_source=tldrdevops" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10254"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before. Coze your way to AI Agent creation. 

Coze Studio is an all-in-one AI agent development tool. Providing the latest large models and tools, various development modes and frameworks, Coze Studio offers the most convenient AI agent development environment, from development to deployment.]]>
            </summary>
            <updated>2025-09-17T14:51:42+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10253</id>
            <title type="text"><![CDATA[AutoGen]]></title>
            <link rel="alternate" href="https://microsoft.github.io/autogen/stable/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10253"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A framework for building AI agents and applications.

AutoGen is a framework for creating multi-agent AI applications that can act autonomously or work alongside humans.

- [AutoGen @ GitHub](https://github.com/microsoft/autogen).

Related contents:

- [Don’t Build Multi-Agents @ Cognition](https://cognition.ai/blog/dont-build-multi-agents#principles-of-context-engineering).]]>
            </summary>
            <updated>2025-09-17T14:32:23+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10249</id>
            <title type="text"><![CDATA[🌊 Claude-Flow]]></title>
            <link rel="alternate" href="https://github.com/ruvnet/claude-flow" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10249"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[AI Orchestration Platform

 🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, distributed swarm intelligence, RAG integration, and native Claude Code support via MCP protocol. Ranked #1 in agent-based frameworks.]]>
            </summary>
            <updated>2025-09-17T11:39:20+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10246</id>
            <title type="text"><![CDATA[Agent Payments Protocol (AP2)]]></title>
            <link rel="alternate" href="https://ap2-protocol.org/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10246"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Building a Secure and Interoperable Future for AI-Driven Payments. 

- [Agent Payments Protocol (AP2) @ GitHub](https://github.com/google-agentic-commerce/AP2).

Related contents:

- [ Google&amp;#039;s new open protocol secures AI agent transactions - and 60 companies already support it  @ ZDNET](https://www.zdnet.com/article/googles-new-open-protocol-secures-ai-agent-transactions-and-60-companies-already-support-it/).]]>
            </summary>
            <updated>2025-09-17T11:23:10+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10227</id>
            <title type="text"><![CDATA[Agent Client Protocol]]></title>
            <link rel="alternate" href="https://agentclientprotocol.com/overview/introduction" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10227"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A protocol for connecting any editor to any agent.

The Agent Client Protocol standardizes communication between code editors (IDEs, text-editors, etc.) and coding agents (programs that use generative AI to autonomously modify code).

- [Agent Client Protocol @ GitHub](https://github.com/zed-industries/agent-client-protocol).

Related contents:

- [Bring Your Own Agent to Zed — Featuring Gemini CLI @ Zed](https://zed.dev/blog/bring-your-own-agent-to-zed).
- [Episode \#112: A new direction for AI developer tooling @ Changelog &amp;amp; Friends](https://changelog.com/friends/112).]]>
            </summary>
            <updated>2025-10-14T05:49:41+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10198</id>
            <title type="text"><![CDATA[SHAI]]></title>
            <link rel="alternate" href="https://labs.ovhcloud.com/en/shai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10198"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[SHAI — Your AI-powered coding assistant.
shai is a coding agent, your pair programming buddy that lives in the terminal. Written in rust with love &amp;lt;3 

SHAI is a cutting-edge, terminal-based AI assistant designed to simplify your day-to-day development tasks. Whether you&amp;#039;re building a website, editing files, running shell commands, or automating complex workflows, Shai has got you covered — all from the comfort of your terminal.

- [SHAI @ GitHub](https://github.com/ovh/shai).

Related contents:

- [SHAI - Le développeur qui vit dans votre terminal @ Korben :fr:](https://korben.info/shai-ovhcloud-outil-dev-ia.html).]]>
            </summary>
            <updated>2025-09-15T09:26:13+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10188</id>
            <title type="text"><![CDATA[Terraform MCP Server]]></title>
            <link rel="alternate" href="https://github.com/hashicorp/terraform-mcp-server" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10188"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The Terraform MCP Server provides seamless integration with Terraform ecosystem, enabling advanced automation and interaction capabilities for Infrastructure as Code (IaC) development. 

Related contents:

- [Terraform + MCP: Your Fast Track to Smarter, Faster Infrastructure @ GenusofTechnology&amp;#039;s GitHub](https://medium.com/genusoftechnology/terraform-mcp-your-fast-track-to-smarter-faster-infrastructure-3b343a1b1cef).
- [Terraforming With AI @  Zachary Loeber&amp;#039;s dev.to](https://dev.to/zloeber/terraforming-with-ai-g0o).]]>
            </summary>
            <updated>2025-10-10T13:53:25+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10164</id>
            <title type="text"><![CDATA[Serena]]></title>
            <link rel="alternate" href="https://github.com/oraios/serena" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10164"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A powerful coding agent toolkit providing semantic retrieval and editing capabilities (MCP server &amp;amp; other integrations).

🚀 Serena is a powerful coding agent toolkit capable of turning an LLM into a fully-featured agent that works directly on your codebase. Unlike most other tools, it is not tied to an LLM, framework or an interface, making it easy to use it in a variety of ways.

Related contents:

- [Accelerate developer productivity with these 9 open source AI and MCP projects @ GitHub blog](https://github.blog/open-source/accelerate-developer-productivity-with-these-9-open-source-ai-and-mcp-projects/).]]>
            </summary>
            <updated>2025-10-27T14:07:03+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10146</id>
            <title type="text"><![CDATA[Dosu |]]></title>
            <link rel="alternate" href="https://dosu.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10146"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Your best engineers shouldn&amp;#039;t Q&amp;amp;A all day.
 
Dosu is an AI-powered Github maintainer agent. Dosu helps open source maintainers encourage contributors, organize issues, triage bugs, answer questions, and more.

Dosu turns your codebase into a living knowledge base that every team member can understand—from engineering to operations—so builders can build.

Related contents:

- [How TriliumNext Revitalized an Abandoned Open Source Project with Dosu&amp;#039;s Help @ Dosu blog](https://dosu.dev/blog/how-triliumnext-revitalized-an-abandoned-open-source-project-with-dosus-help).]]>
            </summary>
            <updated>2025-09-12T07:08:11+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10140</id>
            <title type="text"><![CDATA[ARK - Agentic Runtime for Kubernetes]]></title>
            <link rel="alternate" href="https://mckinsey.github.io/agents-at-scale-ark/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10140"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[ARK extends Kubernetes with custom resources that make agents, teams, MCP tools, and workflows first-class citizens in your cluster.

 Provider-agnostic operations for agentic resources. ARK codifies patterns and practices developed across dozens of agentic application projects. 

- [⚒️ ark @ GitHub](https://github.com/mckinsey/agents-at-scale-ark).]]>
            </summary>
            <updated>2025-09-12T06:36:15+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10096</id>
            <title type="text"><![CDATA[Archon OS]]></title>
            <link rel="alternate" href="https://github.com/coleam00/Archon" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10096"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[the knowledge and task management backbone for AI coding assistants.

Archon is the command center for AI coding assistants. For you, it&amp;#039;s a sleek interface to manage knowledge, context, and tasks for your projects. For the AI coding assistant(s), it&amp;#039;s a Model Context Protocol (MCP) server to collaborate on and leverage the same knowledge, context, and tasks. Connect Claude Code, Kiro, Cursor, Windsurf, etc. to give your AI agents access to:]]>
            </summary>
            <updated>2025-09-10T06:22:50+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10016</id>
            <title type="text"><![CDATA[Parlant]]></title>
            <link rel="alternate" href="https://www.parlant.io/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10016"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Build compliant AI chat agents, in minutes.
 LLM agents built for control. Designed for real-world use. Deployed in minutes. 

Parlant gives you all the structure you need to build customer-facing agents that behave exactly as your business requires

- [Parlant @ GitHub](https://github.com/emcie-co/parlant).]]>
            </summary>
            <updated>2025-09-04T17:08:33+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10002</id>
            <title type="text"><![CDATA[🤗 Hub client library]]></title>
            <link rel="alternate" href="https://huggingface.co/docs/huggingface_hub/index" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10002"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The huggingface_hub library allows you to interact with the Hugging Face Hub, a machine learning platform for creators and collaborators. Discover pre-trained models and datasets for your projects or play with the hundreds of machine learning apps hosted on the Hub. You can also create and share your own models and datasets with the community. The huggingface_hub library provides a simple way to do all these things with Python.

- [🤗 Python client for the Huggingface Hub @ GitHub](https://github.com/huggingface/huggingface_hub).
- [Hugging Face JS libraries @ GitHub](https://github.com/huggingface/huggingface.js).

Related contents:

- [Tiny Agents in Python: an MCP-powered agent in ~70 lines of code @ Hugging Face](https://huggingface.co/blog/python-tiny-agents).
- [Tiny Agents: an MCP-powered agent in 50 lines of code @ Hugging Face](https://huggingface.co/blog/tiny-agents).]]>
            </summary>
            <updated>2025-09-04T11:53:43+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/10001</id>
            <title type="text"><![CDATA[tiny-agents]]></title>
            <link rel="alternate" href="https://huggingface.co/datasets/tiny-agents/tiny-agents" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/10001"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[In this short article, I will walk you through how I implemented it in Typescript (JS), how you can adopt MCP too and how it&amp;#039;s going to make Agentic AI way simpler going forward.

Related contents:

- [Tiny Agents in Python: an MCP-powered agent in ~70 lines of code @ Hugging Face](https://huggingface.co/blog/python-tiny-agents).
- [Tiny Agents: an MCP-powered agent in 50 lines of code @ Hugging Face](https://huggingface.co/blog/tiny-agents).]]>
            </summary>
            <updated>2025-09-04T11:51:28+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1</id>
            <title type="text"><![CDATA[Sim]]></title>
            <link rel="alternate" href="https://www.sim.ai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Build / Deploy Agent Workflows.

Launch agentic workflows with an open source, user-friendly environment for devs and agents.

 Sim is an open-source AI agent workflow builder. Sim Studio&amp;#039;s interface is a lightweight, intuitive way to quickly build and deploy LLMs that connect with your favorite tools. 

- [Sim @ GitHub](https://github.com/simstudioai/sim).

Related contents:

- [Sim Studio - Créez vos workflows d&amp;#039;agents IA aussi facilement que quand vous dessinez sur Figma @ Korben :fr:](https://korben.info/sim-studio-workflows-agents-ia-open-source.html).]]>
            </summary>
            <updated>2025-12-16T10:25:24+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/7</id>
            <title type="text"><![CDATA[AGENTS.md]]></title>
            <link rel="alternate" href="https://agents.md/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/7"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A simple, open format for guiding coding agents,
used by over 20k open-source projects.

Think of AGENTS.md as a README for agents: a dedicated, predictable place to provide the context and instructions to help AI coding agents work on your project.

- [AGENTS.md @ GitHub](https://github.com/openai/agents.md).

Related contents:

- [Improve your AI code output with AGENTS.md (+ my best tips) @ builder.io](https://www.builder.io/blog/agents-md).
- [\#118 - Les news sur le développement web et l&amp;#039;IA pour septembre 2025 RC1 @ Double Slash :fr:](https://double-slash.dev/podcasts/sept25-rc1/).
- [Optimizing repos for AI @ Tom Bedor&amp;#039;s Blog](https://tombedor.dev/optimizing-repos-for-ai/).
- [How to write a great agents.md: Lessons from over 2,500 repositories @ GitHub Blog](https://github.blog/ai-and-ml/github-copilot/how-to-write-a-great-agents-md-lessons-from-over-2500-repositories/).
- [Writing a good CLAUDE.md @ humanlayer](https://www.humanlayer.dev/blog/writing-a-good-claude-md).
- [Streamlining my user-level CLAUDE.md @ chris dzombak](https://www.dzombak.com/blog/2025/12/streamlining-my-user-level-claude-md/).
- [The Complete Guide to CLAUDE.md @ builder.io](https://www.builder.io/blog/claude-md-guide).
- [How to build self-improving coding agents - Part 1 @ Eric J Ma&amp;#039;s Website](https://ericmjl.github.io/blog/2026/1/17/how-to-build-self-improving-coding-agents-part-1/).
- [AGENTS.md outperforms skills in our agent evals @ Vercel](https://vercel.com/blog/agents-md-outperforms-skills-in-our-agent-evals).
- [Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents? @ arXiv](https://arxiv.org/abs/2602.11988).
- [Knowledge Priming @ martinFowler.com](https://martinfowler.com/articles/reduce-friction-ai/knowledge-priming.html).
- [J&amp;#039;ai mis deux IA en code review l&amp;#039;une contre l&amp;#039;autre — voici ce que ça donne @ Maxence Maireaux :fr:](https://maxence.maireaux.fr/fr/blog/mon-workflow-ia-claude-code-codex/).
- [Filesystems are having a moment @ madalitso.me](https://madalitso.me/notes/why-everyone-is-talking-about-filesystems/).
- [Your Docs Directory Is Doomed @ Jim Yagmin&amp;#039;s Blog](https://yagmin.com/blog/your-docs-directory-is-doomed/).
- [Stop Wasting Hours Writing Unit Tests: Use GitHub Copilot to Explode Code Coverage Fast @ Build5Nines](https://build5nines.com/stop-wasting-hours-writing-unit-tests-use-github-copilot-to-explode-code-coverage-fast/).]]>
            </summary>
            <updated>2026-06-04T07:03:14+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/26</id>
            <title type="text"><![CDATA[Bytebot]]></title>
            <link rel="alternate" href="https://www.bytebot.ai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/26"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The Easiest Way to Build Desktop Agents.
Bytebot is a turn-key container for developers building desktop agents.

 Bytebot is a self-hosted AI desktop agent that automates computer tasks through natural language commands, operating within a containerized Linux desktop environment. 

- [Bytebot @ GitHub](https://github.com/bytebot-ai/bytebot).

Related contents:

- [ByteBot - L&amp;#039;agent IA qui prend le contrôle de votre ordi (mais dans Docker, faut pas déconner) @ Korben :fr:](https://korben.info/bytebot-agent-prend-controle-votre-ordinateur.html).]]>
            </summary>
            <updated>2025-09-08T11:30:29+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/82</id>
            <title type="text"><![CDATA[coderunner-ui]]></title>
            <link rel="alternate" href="https://github.com/instavm/coderunner-ui" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/82"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Chat UI for Coderunner.

coderunner-ui is a local‑first AI workspace that lets you:

- Chat with local or remote LLMs
- Run generated code inside a fully isolated Apple Container VM
- Browse the web and automate tasks via a built‑in headless browser (Playwright) All without sending your data to the cloud.

Related contents:

- [I Want Everything Local — Building My Offline AI Workspace @ InstaVM](https://instavm.io/blog/building-my-offline-ai-workspace).]]>
            </summary>
            <updated>2025-09-17T19:31:15+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/83</id>
            <title type="text"><![CDATA[CodeRunner]]></title>
            <link rel="alternate" href="https://github.com/instavm/coderunner" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/83"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Run AI Generated Code Locally.
A secure local sandbox to run LLM-generated code using Apple containers.

CodeRunner is an MCP (Model Context Protocol) server that executes AI-generated code in a sandboxed environment on your Mac using Apple&amp;#039;s native containers.

Related contents:

- [I Want Everything Local — Building My Offline AI Workspace @ InstaVM](https://instavm.io/blog/building-my-offline-ai-workspace).
- [Accelerate developer productivity with these 9 open source AI and MCP projects @ GitHub blog](https://github.blog/open-source/accelerate-developer-productivity-with-these-9-open-source-ai-and-mcp-projects/).]]>
            </summary>
            <updated>2025-10-27T14:06:34+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/107</id>
            <title type="text"><![CDATA[Omnara]]></title>
            <link rel="alternate" href="https://omnara.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/107"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Your AI workforce launchpad, in your pocket. Talk to Your AI Agents from Anywhere!

Omnara transforms your AI agents (Claude Code, Cursor, GitHub Copilot, and more) from silent workers into communicative teammates. Get real-time visibility into what your agents are doing, respond to their questions instantly, and guide them to success - all from your phone.

- [Omnara @ GitHub](https://github.com/omnara-ai/omnara).]]>
            </summary>
            <updated>2025-10-14T09:44:33+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/170</id>
            <title type="text"><![CDATA[stagewise]]></title>
            <link rel="alternate" href="https://stagewise.io/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/170"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[stagewise is the first frontend coding agent for existing production-grade web apps 🪄 -- Lives inside your browser 💻 -- Makes changes in local codebase 🤓 -- Compatible with all kinds of frameworks and setups 💪 .

- [stagewise @ GitHub](https://github.com/stagewise-io/stagewise).]]>
            </summary>
            <updated>2025-10-29T14:30:21+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/174</id>
            <title type="text"><![CDATA[tambo]]></title>
            <link rel="alternate" href="https://tambo.co/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/174"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Add React UI components to your AI agent.

A React package for building AI-powered applications with generative UI, where users interact through natural language. 

- [tambo  @ GitHub](https://github.com/tambo-ai/tambo).]]>
            </summary>
            <updated>2025-10-27T15:09:14+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/197</id>
            <title type="text"><![CDATA[🧠🤖Deep Agents]]></title>
            <link rel="alternate" href="https://github.com/hwchase17/deepagents?ref=blog.langchain.com" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/197"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Using an LLM to call tools in a loop is the simplest form of an agent. This architecture, however, can yield agents that are “shallow” and fail to plan and act over longer, more complex tasks. Applications like “Deep Research”, &amp;quot;Manus&amp;quot;, and “Claude Code” have gotten around this limitation by implementing a combination of four things: a planning tool, sub agents, access to a file system, and a detailed prompt.

deepagents is a Python package that implements these in a general purpose way so that you can easily create a Deep Agent for your application.]]>
            </summary>
            <updated>2025-10-16T09:08:25+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/226</id>
            <title type="text"><![CDATA[🦌 DeerFlow]]></title>
            <link rel="alternate" href="https://deerflow.tech/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/226"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Deep Research at Your Fingertipsat Your Fingertips

Meet DeerFlow, your personal Deep Research assistant. With powerful tools like search engines, web crawlers, Python and MCP services, it delivers instant insights, comprehensive reports, and even captivating podcasts.

 DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community. 

- [🦌 DeerFlow @ GitHub](https://github.com/bytedance/deer-flow).]]>
            </summary>
            <updated>2025-10-27T15:09:32+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/233</id>
            <title type="text"><![CDATA[MCP-Use]]></title>
            <link rel="alternate" href="https://mcp-use.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/233"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Build and deploy MCP agents.

Spin-up and aggregate MCP servers through a single endpoint and zero friction.

 mcp-use is the easiest way to interact with mcp servers with custom agents.
🌐 MCP-Use is the open source way to connect any LLM to any MCP server and build custom MCP agents that have tool access, without using closed source or application clients.

- [MCP-Use @ GitHub](https://github.com/mcp-use/mcp-use).]]>
            </summary>
            <updated>2025-10-28T10:36:16+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/240</id>
            <title type="text"><![CDATA[GoDoctor]]></title>
            <link rel="alternate" href="https://github.com/danicat/godoctor" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/240"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A Model Context Protocol server for Go developers.

GoDoctor is an intelligent, AI-powered companion for the modern Go developer. It integrates seamlessly with AI-powered IDEs and other development tools through the Model Context Protocol (MCP), providing a suite of powerful features to enhance your workflow.

- [How to Build an MCP Server with Gemini CLI and Go @ danicat.dev](https://danicat.dev/posts/20250729-how-to-build-an-mcp-server-with-gemini-cli-and-go/).]]>
            </summary>
            <updated>2026-04-09T09:11:15+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/245</id>
            <title type="text"><![CDATA[Crush]]></title>
            <link rel="alternate" href="https://github.com/charmbracelet/crush" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/245"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The glamourous AI coding agent for your favourite terminal 💘 

Your new coding bestie, now available in your favourite terminal.
Your tools, your code, and your workflows, wired into your LLM of choice.

Related contents:

- [Self-Hosting AI Models After Claude&amp;#039;s Usage Limits @ Peter Steinberger](https://steipete.me/posts/2025/self-hosting-ai-models).
- [Episode 627: The 2 a.m. Rescue @ Linux Matters](https://linuxunplugged.com/627).
- [Testing out Crush, a TUI based coding agent (in neovim btw) @ Graham Helton](https://grahamhelton.com/blog/crushing-it).
- [Coding for the Future Agentic World @ Elevate](https://addyo.substack.com/p/coding-for-the-future-agentic-world).]]>
            </summary>
            <updated>2025-11-20T08:05:52+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/247</id>
            <title type="text"><![CDATA[Meka Agent]]></title>
            <link rel="alternate" href="https://withmeka.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/247"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[state of the art browsing agent (WebArena 72.7%).

Meka Agent is an open-source, autonomous computer-using agent that delivers state-of-the-art browsing capabilities. The agent works and acts in the same way humans do, by purely using vision as its eyes and acting within a full computer context.

It is designed as a simple, extensible, and customizable framework, allowing flexibility in the choice of models, tools, and infrastructure providers.

- [Meka Agent @ GitHub](https://github.com/trymeka/agent).]]>
            </summary>
            <updated>2025-12-09T11:38:26+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/270</id>
            <title type="text"><![CDATA[Grok CLI]]></title>
            <link rel="alternate" href="https://github.com/superagent-ai/grok-cli" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/270"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[An open-source AI agent that brings the power of Grok directly into your terminal.
A conversational AI CLI tool powered by Grok with intelligent text editor capabilities and tool usage.]]>
            </summary>
            <updated>2025-12-31T08:17:36+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/307</id>
            <title type="text"><![CDATA[Agents.md]]></title>
            <link rel="alternate" href="https://agentsmd.net/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/307"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Agents.md Guide for OpenAI Codex

Learn how to use Agents.md files to enhance OpenAI Codex and other AI agents in navigating your codebases, running tests, and adhering to your project&amp;#039;s standard practices.

Related contents:

- [Docs for AI agents @ https://technicalwriting.dev](https://technicalwriting.dev/ai/agents/).]]>
            </summary>
            <updated>2025-12-31T14:22:35+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/312</id>
            <title type="text"><![CDATA[MCP-UI]]></title>
            <link rel="alternate" href="https://mcpui.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/312"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Interactive UI Components for MCP
SDK for UI over MCP. Create next-gen UI experiences!

Build rich, dynamic user interfaces for your MCP applications with SDKs that bring UI to AI interactions.

- [MCP-UI @ GitHub](https://github.com/idosal/mcp-ui).

Related contents:

- [MCP Apps And Interactive UIs In MCP Clients @ Den Delimarsky](https://den.dev/blog/mcp-apps/).
- [MCP Apps: Extending servers with interactive user interfaces @ Model Context Protocol Blog](https://blog.modelcontextprotocol.io/posts/2025-11-21-mcp-apps/).]]>
            </summary>
            <updated>2026-01-28T13:09:51+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/314</id>
            <title type="text"><![CDATA[any-agent]]></title>
            <link rel="alternate" href="https://mozilla-ai.github.io/any-agent/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/314"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[any-agent is a Python library providing a single interface to different agent frameworks.

- [any-agent @ GitHub](https://github.com/mozilla-ai/any-agent).]]>
            </summary>
            <updated>2025-12-31T14:21:50+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/316</id>
            <title type="text"><![CDATA[kubectl-ai]]></title>
            <link rel="alternate" href="https://github.com/GoogleCloudPlatform/kubectl-ai" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/316"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[AI powered Kubernetes Assistant.

kubectl-ai acts as an intelligent interface, translating user intent into precise Kubernetes operations, making Kubernetes management more accessible and efficient.

Related contents:

- [kubectl AI - AI powered Kubernetes assistant @ Kubesimplify&amp;#039;s YouTube](https://www.youtube.com/watch?v=LFQpuZb_r6s).]]>
            </summary>
            <updated>2026-02-09T06:15:51+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/321</id>
            <title type="text"><![CDATA[Morphik]]></title>
            <link rel="alternate" href="https://www.morphik.ai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/321"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Build Agents that Never Hallucinate.
Deploy the most accurate RAG in the world in two lines of code.

 The most accurate document search and store for building AI apps.

- [Morphik @ GitHub](https://github.com/morphik-org/morphik-core).

Related contents:

- [Don&amp;#039;t bother parsing: Just use images for RAG @ Morphik](https://www.morphik.ai/blog/stop-parsing-docs).]]>
            </summary>
            <updated>2026-01-13T13:25:14+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/327</id>
            <title type="text"><![CDATA[Kiro]]></title>
            <link rel="alternate" href="https://kiro.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/327"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The AI IDE for prototype to production.

Kiro is an agentic IDE that helps you go from prototype to production with spec-driven development, agent hooks, and natural language coding assistance. Build faster with AI-powered features that understand your entire codebase, turn prompts into structured specs, and automate repetitive tasks.

- [Kiro @ GitHub](https://github.com/kirodotdev/Kiro).

Related contents:

- [Episode \#662: Spec-driven development with Kiro @ Changelog Interviews](https://changelog.com/podcast/662).
- [The uncomfortable truth about vibe coding @ RedHat Developer](https://developers.redhat.com/articles/2026/02/17/uncomfortable-truth-about-vibe-coding).]]>
            </summary>
            <updated>2026-02-24T07:19:57+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/328</id>
            <title type="text"><![CDATA[Conductor]]></title>
            <link rel="alternate" href="https://conductor.build/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/328"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Run a bunch of Claude Codes in parallel.

Each Claude gets an isolated workspace. See who’s working, see who’s stuck, and what’s changed.]]>
            </summary>
            <updated>2026-01-20T15:24:56+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/329</id>
            <title type="text"><![CDATA[🚀 Kilo Code]]></title>
            <link rel="alternate" href="https://github.com/Kilo-Org/kilocode" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/329"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Open Source AI coding assistant for planning, building, and fixing code. We&amp;#039;re a superset of Roo, Cline, and our own features.]]>
            </summary>
            <updated>2026-01-20T15:25:02+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/331</id>
            <title type="text"><![CDATA[am-i-vibing]]></title>
            <link rel="alternate" href="https://github.com/ascorbic/am-i-vibing" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/331"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Detect agentic coding environments and AI editors.

Detect agentic coding environments and AI assistant tools. This library allows CLI tools and Node apps to detect when they&amp;#039;re being executed by AI agents. This enables them to adapt by, for example, providing different output formats or logs.]]>
            </summary>
            <updated>2026-01-20T15:25:20+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/357</id>
            <title type="text"><![CDATA[Agent Development Kit]]></title>
            <link rel="alternate" href="https://google.github.io/adk-docs/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/357"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[An open-source, code-first Python or Java toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

Agent Development Kit (ADK) is a flexible and modular framework for developing and deploying AI agents. While optimized for Gemini and the Google ecosystem, ADK is model-agnostic, deployment-agnostic, and is built for compatibility with other frameworks. ADK was designed to make agent development feel more like software development, to make it easier for developers to create, deploy, and orchestrate agentic architectures that range from simple tasks to complex workflows.

- [Agent Development Kit (ADK) Python @ GitHub](https://github.com/google/adk-python).
- [Agent Development Kit (ADK) Java @ GitHub](https://github.com/google/adk-java).
- [Agent Development Kit (ADK) for Go @ GitHub](https://github.com/google/adk-go).

Related contents:

- [ADK architecture: When to use sub-agents versus agents as tools @ Google Cloud Blog](https://cloud.google.com/blog/topics/developers-practitioners/where-to-use-sub-agents-versus-agents-as-tools).]]>
            </summary>
            <updated>2025-11-19T06:35:25+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/380</id>
            <title type="text"><![CDATA[Bitwarden MCP Server]]></title>
            <link rel="alternate" href="https://github.com/bitwarden/mcp-server" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/380"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[MCP server for interaction with the Bitwarden vault.

Model Context Protocol (MCP) server that enables interaction with the Bitwarden password manager vault via the MCP protocol. The server allows AI models to securely communicate with a user&amp;#039;s Bitwarden vault through defined tool interfaces.

Related contents:

- [Bitwarden launches MCP server to securely connect AI agents with your passwords @ NERDS.xyz](https://nerds.xyz/2025/07/bitwarden-mcp-server-secure-ai/).]]>
            </summary>
            <updated>2026-02-12T12:59:17+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/382</id>
            <title type="text"><![CDATA[Vibe Kanban]]></title>
            <link rel="alternate" href="https://www.vibekanban.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/382"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Orchestrate AI Coding Agents.
Kanban board to manage your AI coding agents.

AI coding agents are increasingly writing the world&amp;#039;s code and human engineers now spend the majority of their time planning, reviewing, and orchestrating tasks. Vibe Kanban streamlines this process.

- [Vibe Kanban @ GitHub](https://github.com/BloopAI/vibe-kanban).

Related contents:

- [Software Engineering Is Becoming Plan and Review — Louis Knight-Webb, Vibe Kanban @ AI Engineer&amp;#039;s YouTube](https://www.youtube.com/watch?v=W76woOYHlvY).
- [\#131: News Mai 2026, TypeScript 7 en beta, faux package TanStack et agent Cursor destructeur @ Double Slash :fr:](https://double-slash.dev/podcasts/news-mai26/).]]>
            </summary>
            <updated>2026-06-04T05:37:24+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/391</id>
            <title type="text"><![CDATA[BrowserOS]]></title>
            <link rel="alternate" href="https://www.browseros.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/391"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The Open-Source Agentic Browser. Your Browser, Reimagined.

We believe browsers must be open source, not owned by search or ad companies. And the future is AI agents automating your work locally and securely. We&amp;#039;re building the best browser for that future.

- [BrowserOS @ GitHub](https://github.com/browseros-ai/BrowserOS).]]>
            </summary>
            <updated>2026-01-20T15:31:48+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/401</id>
            <title type="text"><![CDATA[MCP-B]]></title>
            <link rel="alternate" href="https://mcp-b.ai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/401"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Model Context Protocolfor the Browser

Browser-based Model Context Protocol (MCP) implementation that enables AI assistants to interact with web applications through standardized MCP tools.

Today&amp;#039;s AI automation is like using a robot to read your screen and click buttons. MCP-B gives AI direct access to your website&amp;#039;s functions instead.

- [MCP-B @ GitHub](https://github.com/MiguelsPizza/WebMCP).

Related contents:

- [\#127 - News Février 2026, du WebMCP, des agents spammeurs et du Markdown @ Double Slash :fr:](https://double-slash.dev/podcasts/news-fev26/).]]>
            </summary>
            <updated>2026-02-20T07:08:41+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/406</id>
            <title type="text"><![CDATA[Graphiti]]></title>
            <link rel="alternate" href="https://help.getzep.com/graphiti/getting-started/welcome" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/406"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Build Real-Time Knowledge Graphs for AI Agents.

Graphiti is a Python framework for building temporally-aware knowledge graphs designed for AI agents. It enables real-time incremental updates to knowledge graphs without batch recomputation, making it suitable for dynamic environments where relationships and information evolve over time.

- [Graphiti @ GitHub](https://github.com/getzep/graphiti).]]>
            </summary>
            <updated>2026-02-12T12:59:26+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/407</id>
            <title type="text"><![CDATA[OpenCLI]]></title>
            <link rel="alternate" href="https://opencli.org/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/407"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The OpenCLI specification (OCS) defines a standard, platform and language agnostic interface to CLI applications which allows both humans and computers to understand how a CLI tool should be invoked without access to source code or documentation.

An OpenCLI Description can be used by documentation software to display usage of a tool, or code generation tools to create clients for interoping with a CLI tool.

- [OpenCLI @ GitHub](https://github.com/spectreconsole/open-cli).

Related contents:

- [Introducing OpenCLI @ Patrik Svensson](https://patriksvensson.se/posts/2025/07/introducing-open-cli).]]>
            </summary>
            <updated>2025-08-28T17:05:51+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/415</id>
            <title type="text"><![CDATA[Backlog.md]]></title>
            <link rel="alternate" href="https://github.com/MrLesk/Backlog.md" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/415"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Markdown‑native Task Manager &amp;amp; Kanban visualizer for any Git repository.

A tool for managing project collaboration between humans and AI Agents in a git ecosystem.

Backlog.md turns any folder with a Git repo into a self‑contained project board
powered by plain Markdown files and a zero‑config CLI.]]>
            </summary>
            <updated>2025-08-28T17:06:48+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/416</id>
            <title type="text"><![CDATA[Amp]]></title>
            <link rel="alternate" href="https://ampcode.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/416"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Amp is an agentic coding tool engineered to maximize what’s possible with today’s frontier models—autonomous reasoning, comprehensive code editing, and complex task execution.

Related content:

- [How to Build an Agent, or: The Emperor Has No Clothes @ Amp](https://ampcode.com/how-to-build-an-agent).
- [Episode \#648: Agent, take the wheel @ Changelog Interviews](https://changelog.com/podcast/648).
- [Self-Hosting AI Models After Claude&amp;#039;s Usage Limits @ Peter Steinberger](https://steipete.me/posts/2025/self-hosting-ai-models).
- [Episode \#658: Flowing with agents @ Changelog Interviews](https://changelog.com/podcast/658).]]>
            </summary>
            <updated>2025-09-23T07:31:41+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/419</id>
            <title type="text"><![CDATA[opencode]]></title>
            <link rel="alternate" href="https://opencode.ai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/419"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[AI coding agent built for the terminal.

- [opencode @ GitHub](https://github.com/sst/opencode).

Related contents:

- [Self-Hosting AI Models After Claude&amp;#039;s Usage Limits @ Peter Steinberger](https://steipete.me/posts/2025/self-hosting-ai-models).
- [OpenCode vs Claude Code @ builder.io](https://www.builder.io/blog/opencode-vs-claude-code).
- [How to Integrate AI into Your Terminal Using OpenCode @ freeCodeCamp](https://www.freecodecamp.org/news/integrate-ai-into-your-terminal-using-opencode/).
- [Subagents: When and How to Use Them @ builder.io](https://www.builder.io/blog/subagents).]]>
            </summary>
            <updated>2026-02-05T08:34:35+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/421</id>
            <title type="text"><![CDATA[cursor-tools]]></title>
            <link rel="alternate" href="https://github.com/eastlondoner/vibe-tools" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/421"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Give Cursor Agent an AI Team and Advanced Skills]]>
            </summary>
            <updated>2025-08-28T17:07:49+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/434</id>
            <title type="text"><![CDATA[WASM Agents Blueprint]]></title>
            <link rel="alternate" href="https://github.com/mozilla-ai/wasm-agents-blueprint" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/434"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Testing WASM-powered AI agents.

This Blueprint demonstrates how to run AI agents directly in the browser using WebAssembly (WASM) through Pyodide and the OpenAI Agents Python SDK. Experience the power of Python-based AI agents without external dependencies – agent code runs directly in your web browser. 

Related contents:

- [Wasm-agents: AI agents running in your browser @ Mozilla.ai](https://blog.mozilla.ai/wasm-agents-ai-agents-running-in-your-browser/).]]>
            </summary>
            <updated>2025-08-28T17:09:54+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/463</id>
            <title type="text"><![CDATA[Claude Swarm]]></title>
            <link rel="alternate" href="https://github.com/parruda/claude-swarm" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/463"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Easily launch a Claude Code session that is connected to a swarm of Claude Code Agents.

Claude Swarm orchestrates multiple Claude Code instances as a collaborative AI development team. It enables running AI agents with specialized roles, tools, and directory contexts, communicating via MCP (Model Context Protocol) in a tree-like hierarchy. Define your swarm topology in simple YAML and let Claude instances delegate tasks through connected instances. Perfect for complex projects requiring specialized AI agents for frontend, backend, testing, DevOps, or research tasks.

Related contents:

- [Using Claude-Swarm to Upgrade Ruby Projects @ dBlock.org](https://code.dblock.org/2025/06/21/using-claude-swarm-to-upgrade-ruby-projects.html).]]>
            </summary>
            <updated>2025-08-28T17:14:52+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/465</id>
            <title type="text"><![CDATA[OpenEvolve]]></title>
            <link rel="alternate" href="https://github.com/codelion/openevolve" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/465"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[An open-source implementation of the AlphaEvolve system described in the Google DeepMind paper &amp;quot;AlphaEvolve: A coding agent for scientific and algorithmic discovery&amp;quot; (2025).]]>
            </summary>
            <updated>2025-08-28T17:14:54+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/472</id>
            <title type="text"><![CDATA[Comet Browser by Perplexity]]></title>
            <link rel="alternate" href="https://www.perplexity.ai/comet" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/472"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Related contents:

- [Perplexity’s Comet Browser is Now Available in Beta @ Analytics India Magazine](https://analyticsindiamag.com/ai-news-updates/perplexitys-comet-browser-is-now-available-in-beta/).
- [Comet - Le navigateur IA de Perplexity débarque sur Windows @ Korben :fr:](https://korben.info/comet-navigateur-ia-perplexity-windows-beta.html).
- [Agentic Browser Security: Indirect Prompt Injection in Perplexity Comet @ Brave](https://brave.com/blog/comet-prompt-injection/).]]>
            </summary>
            <updated>2025-09-19T05:55:56+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/480</id>
            <title type="text"><![CDATA[OpenTofu MCP Server]]></title>
            <link rel="alternate" href="https://github.com/opentofu/opentofu-mcp-server" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/480"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A Model Context Protocol (MCP) server for accessing the OpenTofu Registry. This server allows language model assistants to search for and retrieve information about OpenTofu providers, modules, resources, and data sources.]]>
            </summary>
            <updated>2025-08-28T17:17:58+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/490</id>
            <title type="text"><![CDATA[cognee]]></title>
            <link rel="alternate" href="https://www.cognee.ai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/490"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Improve your AI infrastructure - AI memory engine.
Memory for AI Agents in 5 lines of code.

Build dynamic memory for Agents and replace RAG using scalable, modular ECL (Extract, Cognify, Load) pipelines.

- [cognee @ GitHub](https://github.com/topoteretes/cognee).]]>
            </summary>
            <updated>2025-08-28T17:18:55+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/502</id>
            <title type="text"><![CDATA[Pickaxe]]></title>
            <link rel="alternate" href="https://pickaxe.hatchet.run/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/502"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Build agents that scale with a zero-cost abstraction. 

Pickaxe is a simple Typescript library for building AI agents that are fault-tolerant and scalable. It handles the complexities of durable execution, queueing and scheduling, allowing you to focus on writing core business logic. It is not a framework.

- [Pickaxe @ GitHub](https://github.com/hatchet-dev/pickaxe).]]>
            </summary>
            <updated>2025-08-28T17:21:58+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/505</id>
            <title type="text"><![CDATA[AG-UI Protocol]]></title>
            <link rel="alternate" href="https://docs.ag-ui.com/introduction" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/505"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Agent User Interaction Protocol.

AG-UI is a lightweight, event-based protocol that standardizes how AI agents connect to front-end applications. Built for simplicity and flexibility, it enables seamless integration between your AI agents and user interfaces.

AG-UI standardizes how front-end applications connect to AI agents through an open protocol. Think of it as a universal translator for AI-driven systems- no matter what language an agent speaks: AG-UI ensures fluent communication.

- [AG-UI @ GitHub](https://github.com/ag-ui-protocol/ag-ui).]]>
            </summary>
            <updated>2025-08-28T17:21:59+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/506</id>
            <title type="text"><![CDATA[Nxtscape Browser]]></title>
            <link rel="alternate" href="http://blank" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/506"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Your browser, with AI superpowers 🚀.
 Nxtscape is an open-source agentic browser. 

🌐 Nxtscape is an open-source agentic browser that runs AI agents locally. Your privacy-first alternative to Arc, Dia, and Perplexity Comet.

- [Nxtscape Browser @ GitHub](https://github.com/nxtscape/nxtscape).]]>
            </summary>
            <updated>2025-08-28T17:21:59+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/511</id>
            <title type="text"><![CDATA[ToolHive]]></title>
            <link rel="alternate" href="https://github.com/stacklok/toolhive" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/511"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[simplify and secure MCP servers. ToolHive makes deploying MCP servers easy, secure and fun.

Run any Model Context Protocol (MCP) server — securely, instantly, anywhere.

ToolHive is the easiest way to discover, deploy, and manage MCP servers. Launch any MCP server in a locked-down container with a single command. No manual setup, no security headaches, no runtime hassles.]]>
            </summary>
            <updated>2025-08-28T17:22:57+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/520</id>
            <title type="text"><![CDATA[EnrichMCP]]></title>
            <link rel="alternate" href="https://github.com/featureform/enrichmcp" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/520"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[EnrichMCP is a Python framework that helps AI agents understand and navigate your data. Built on MCP (Model Context Protocol), it adds a semantic layer that turns your data model into typed, discoverable tools - like an ORM for AI.]]>
            </summary>
            <updated>2025-08-28T17:23:59+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/521</id>
            <title type="text"><![CDATA[Featureform]]></title>
            <link rel="alternate" href="https://www.featureform.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/521"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The Data Layer for Agentic Enrichment and ML Features. The Virtual Feature Store. Turn your existing data infrastructure into a feature store. 

Featureform is a virtual feature store. It enables data scientists to define, manage, and serve their ML model&amp;#039;s features. Featureform sits atop your existing infrastructure and orchestrates it to work like a traditional feature store. By using Featureform, a data science team can solve the following organizational problems:

- [Featureform @ GitHub](https://github.com/featureform/featureform).]]>
            </summary>
            <updated>2025-08-28T17:25:57+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/559</id>
            <title type="text"><![CDATA[Forge Code]]></title>
            <link rel="alternate" href="https://forgecode.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/559"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The AI Shell.  AI enabled pair programmer for Claude, GPT, O Series, Grok, Deepseek, Gemini and 300+ models.

A comprehensive coding agent that integrates AI capabilities with your development environment.

- [Forge @ GitHub](https://github.com/antinomyhq/forge).]]>
            </summary>
            <updated>2025-08-28T17:31:00+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/565</id>
            <title type="text"><![CDATA[Metorial MCP Index]]></title>
            <link rel="alternate" href="https://metorial.com/marketplace" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/565"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[An ever growing list of open source MCP servers 📡 📁 🚀 

Explore thousands of MCP servers. And connect to them in a single function call.

- [MCP Index @ GitHub](https://github.com/metorial/mcp-index).]]>
            </summary>
            <updated>2025-08-28T17:32:02+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/581</id>
            <title type="text"><![CDATA[container-use]]></title>
            <link rel="alternate" href="https://github.com/dagger/container-use" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/581"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Development environments for coding agents. Enable multiple agents to work safely and independently with your preferred stack. 

Container Use lets each of your coding agents have their own containerized environment. Go from babysitting one agent at a time to enabling multiple agents to work safely and independently with your preferred stack.]]>
            </summary>
            <updated>2025-08-28T17:34:09+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/598</id>
            <title type="text"><![CDATA[Paws-on-MCP]]></title>
            <link rel="alternate" href="https://github.com/hemanth/paws-on-mcp" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/598"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Unified MCP Server Implementation.

A comprehensive Model Context Protocol (MCP) server implementing the latest MCP 2025-03-26 specification. Demonstrates MCP capabilities including tools, resources, prompts, roots, and enhanced sampling with model preferences. Features HackerNews and GitHub API integrations with AI-powered analysis through advanced MCP sampling.]]>
            </summary>
            <updated>2025-08-28T17:38:06+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/633</id>
            <title type="text"><![CDATA[FastMCP]]></title>
            <link rel="alternate" href="https://gofastmcp.com/getting-started/welcome" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/633"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The fast, Pythonic way to build MCP servers and clients.

The Model Context Protocol (MCP) is a new, standardized way to provide context and tools to your LLMs, and FastMCP makes building MCP servers and clients simple and intuitive. Create tools, expose resources, define prompts, and more with clean, Pythonic code.

- [FastMCP @ GitHub](https://github.com/jlowin/fastmcp).
- [FastMCP Cloud](https://fastmcp.cloud/).

Related contents:

- [An Open-Source Maintainer&amp;#039;s Guide to Saying No @ Mostly Harmless](https://www.jlowin.dev/blog/oss-maintainers-guide-to-saying-no).
- [Learn MCP Essentials and How to Create Secure Agent Interfaces with FastMCP @ freeCodeCamp](https://www.freecodecamp.org/news/learn-mcp-essentials-and-how-to-create-secure-agent-interfaces-with-fastmcp/).]]>
            </summary>
            <updated>2025-10-22T14:15:42+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/653</id>
            <title type="text"><![CDATA[Uzi]]></title>
            <link rel="alternate" href="http://blank" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/653"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[CLI for running large numbers of coding agents in parallel with git worktrees 

- [Uzi @ GitHub](https://github.com/devflowinc/uzi).

Related contents:

- [LLM Codegen go Brrr – Parallelization with Git Worktrees and Tmux @ Nick Khami&amp;#039;s Blog](https://www.skeptrune.com/posts/git-worktrees-agents-and-tmux/).]]>
            </summary>
            <updated>2025-08-28T17:46:18+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/654</id>
            <title type="text"><![CDATA[Claude Squad]]></title>
            <link rel="alternate" href="https://smtg-ai.github.io/claude-squad/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/654"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Manage multiple AI agents like Claude Code, Aider, Codex, and Amp. 10x your productivity.

- [Claude Squad @ GitHub](https://github.com/smtg-ai/claude-squad).

Related contents:

- [LLM Codegen go Brrr – Parallelization with Git Worktrees and Tmux @ Nick Khami&amp;#039;s Blog](https://www.skeptrune.com/posts/git-worktrees-agents-and-tmux/).]]>
            </summary>
            <updated>2025-08-28T17:46:18+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/664</id>
            <title type="text"><![CDATA[🐚 MCP Server in Bash]]></title>
            <link rel="alternate" href="https://github.com/muthuishere/mcp-server-bash-sdk" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/664"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A lightweight, zero-overhead implementation of the Model Context Protocol (MCP) server in pure Bash.

Why? Most MCP servers are just API wrappers with schema conversion. This implementation provides a zero-overhead alternative to Node.js, Python, or other heavy runtimes.]]>
            </summary>
            <updated>2025-08-28T17:48:10+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/670</id>
            <title type="text"><![CDATA[OneMCP]]></title>
            <link rel="alternate" href="https://onemcp.io/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/670"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Run MCPs without the complexity ⚡️

OneMCP is an app that lets you run any MCP without the complexity of downloading repos, reading docs, or setting up servers.

Related contents:

- [OneMCP - Pour faire tourner des serveurs MCP facilement @ Korben :fr:](https://korben.info/onemcp-serveur-mcp-anthropic-facile.html).]]>
            </summary>
            <updated>2025-08-28T17:50:22+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/688</id>
            <title type="text"><![CDATA[🦉 OWL]]></title>
            <link rel="alternate" href="https://github.com/camel-ai/owl" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/688"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation.

🦉 OWL is a cutting-edge framework for multi-agent collaboration that pushes the boundaries of task automation, built on top of the CAMEL-AI Framework.]]>
            </summary>
            <updated>2025-08-28T17:52:11+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/704</id>
            <title type="text"><![CDATA[Airweave]]></title>
            <link rel="alternate" href="https://airweave.ai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/704"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Turn Apps Into Agent-Ready Knowledge.
Empower Agents with Deep Knowledge About Their Users. 
Give Users the Experience They Deserve

Airweave is a tool that lets agents semantically search any app. It&amp;#039;s MCP compatible and seamlessly connects any app, database, or API, to transform their contents into agent-ready knowledge.

Airweave simplifies the process of making information retrievable for your agent. Whether you have structured or unstructured data, Airweave helps you break it into processable entities, store the data and make it retrievable through REST and MCP endpoints.

- [Airweave @ GitHub](https://github.com/airweave-ai/airweave).]]>
            </summary>
            <updated>2025-08-28T17:55:12+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/732</id>
            <title type="text"><![CDATA[Open Computer Agent]]></title>
            <link rel="alternate" href="https://huggingface.co/spaces/smolagents/computer-agent" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/732"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[a Hugging Face Space by smolagents.

open source agent taking control of a computer desktop.

Related contents:

- [Open Computer Agent - J&amp;#039;ai testé le robot virtuel open source qui utilise votre PC à votre place @ Korben :fr:](https://korben.info/open-computer-agent-robot-virtuel-ia-test.html).]]>
            </summary>
            <updated>2025-08-28T17:59:17+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/736</id>
            <title type="text"><![CDATA[GitHub MCP Server]]></title>
            <link rel="alternate" href="https://github.com/github/github-mcp-server" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/736"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[GitHub&amp;#039;s official MCP Server.

The GitHub MCP Server is a Model Context Protocol (MCP) server that provides seamless integration with GitHub APIs, enabling advanced automation and interaction capabilities for developers and tools.

Related contents:

- [A practical guide on how to use the GitHub MCP server @ GitHub blog](https://github.blog/ai-and-ml/generative-ai/a-practical-guide-on-how-to-use-the-github-mcp-server/).
- [Why we open sourced our MCP server, and what it means for you @ GitHub blog](https://github.blog/open-source/maintainers/why-we-open-sourced-our-mcp-server-and-what-it-means-for-you/).]]>
            </summary>
            <updated>2025-08-28T18:00:15+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/745</id>
            <title type="text"><![CDATA[Kortix Suna]]></title>
            <link rel="alternate" href="https://www.suna.so/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/745"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Suna by Kortix – is a generalist AI Agent that acts on your behalf.

Suna is a fully open source AI assistant that helps you accomplish real-world tasks with ease. Through natural conversation, Suna becomes your digital companion for research, data analysis, and everyday challenges—combining powerful capabilities with an intuitive interface that understands what you need and delivers results.

- [Suna @ GitHub](https://github.com/kortix-ai/suna).]]>
            </summary>
            <updated>2025-08-28T18:02:20+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/755</id>
            <title type="text"><![CDATA[Klavis AI]]></title>
            <link rel="alternate" href="https://www.klavis.ai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/755"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[MCP Integrationfor AI Applications

The best way to get access to production-ready MCP servers at scale.

Klavis AI makes it effortless to connect to production-ready MCP servers &amp;amp; clients at scale. Integrate with your AI application in under a minute, and scale to millions of users using our open-source infrastructure, hosted servers, and multi-platform clients!

- [Klavis AI @ GitHub](https://github.com/Klavis-AI/klavis).]]>
            </summary>
            <updated>2025-08-28T18:03:18+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/759</id>
            <title type="text"><![CDATA[ACI.dev]]></title>
            <link rel="alternate" href="https://www.aci.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/759"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[integrate LLM with any tool. ACI: Open-Source Infra to Power Unified MCP Servers.

ACI.dev is the open-source infrastructure layer for AI-agent tool-use. It gives your agents intent-aware access to 600+ tools with multi-tenant auth, granular permissions, and dynamic tool discovery—exposed as either direct function calls or through a Unified Model-Context-Protocol (MCP) server. 

 ACI.dev is the open source platform that connects your AI agents to 600+ tool integrations with multi-tenant auth, granular permissions, and access through direct function calling or a unified MCP server. 

- [ACI.dev @ GitHub](https://github.com/aipotheosis-labs/aci).]]>
            </summary>
            <updated>2025-08-28T18:04:17+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/766</id>
            <title type="text"><![CDATA[Taskmaster AI]]></title>
            <link rel="alternate" href="https://www.task-master.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/766"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The PM for your AI agent.
 An AI-powered task-management system you can drop into Cursor, Lovable, Windsurf, Roo, and others. 

Taskmaster is your AI&amp;#039;s personal project manager. Organize, research, expand, prioritize, and ship tasks effortlessly. Enjoy permanent context, zero drift &amp;amp; instant clarity. It&amp;#039;s free, open-source &amp;amp; API-friendly. Let&amp;#039;s vibe productively.

- [Taskmaster AI @ GitHub](https://github.com/eyaltoledano/claude-task-master).]]>
            </summary>
            <updated>2025-08-28T18:06:20+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/768</id>
            <title type="text"><![CDATA[Desktop Commander MCP]]></title>
            <link rel="alternate" href="https://desktopcommander.app/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/768"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Terminal Commands and File Editing for Claude.

This is MCP server for Claude that gives it terminal control, file system search and diff file editing capabilities.

- [Desktop Commander MCP @ GitHub](https://github.com/wonderwhy-er/DesktopCommanderMCP).]]>
            </summary>
            <updated>2025-08-28T18:06:21+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/781</id>
            <title type="text"><![CDATA[AWS Cost Explorer and Amazon Bedrock Model Invocation Logs MCP Server &amp;amp; Client]]></title>
            <link rel="alternate" href="https://github.com/aarora79/aws-cost-explorer-mcp-server" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/781"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[MCP server for understanding AWS spend.

An MCP server for getting AWS spend data via Cost Explorer and Amazon Bedrock usage data via Model invocation logs in Amazon Cloud Watch through Anthropic&amp;#039;s MCP (Model Control Protocol).]]>
            </summary>
            <updated>2025-08-28T18:08:18+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/787</id>
            <title type="text"><![CDATA[Vantage MCP Server]]></title>
            <link rel="alternate" href="https://github.com/vantage-sh/vantage-mcp-server" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/787"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[MCP Server to fetch costs and usage data from your Vantage account. 

Use natural language to explore your organization’s cloud costs via MCP clients, like Claude, Cursor, and others. Ask questions about your organization&amp;#039;s previous and current cloud cost spend, cost tagging, provider integrations, and more.]]>
            </summary>
            <updated>2025-08-28T18:10:21+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/795</id>
            <title type="text"><![CDATA[🚀 operative.sh web-eval-agent MCP Server]]></title>
            <link rel="alternate" href="https://www.operative.sh/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/795"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[An MCP server that autonomously evaluates web applications. 

Browser Agents to vibe-test your web app. Let browser agents vibe-test your vibe-coding.

10x your vibe coding by giving your coding agent a browser agent that can vibe-test web applications via MCP.

- [web-eval-agent MCP Server @ GitHub](https://github.com/Operative-Sh/web-eval-agent).]]>
            </summary>
            <updated>2025-08-28T18:10:26+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/799</id>
            <title type="text"><![CDATA[CleverBee]]></title>
            <link rel="alternate" href="https://cleverb.ee/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/799"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Transparent AI, Rooted in Research, Open to All.
The Open Source Deep Researcher Tool.
AI-Powered Online Data Information Synthesis Assistant.

CleverBee is a powerful Python-based research assistant agent using Large Language Models (LLMs) like Claude and Gemini, Playwright for web browsing, and Chainlit for an interactive UI. It performs research assistance by browsing the web, extracting content (HTML), cleaning it, and synthesizing findings based on user research topics.

- [CleverBee @ GitHub](https://github.com/SureScaleAI/cleverbee).]]>
            </summary>
            <updated>2025-08-28T18:10:29+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/804</id>
            <title type="text"><![CDATA[TmuxAI]]></title>
            <link rel="alternate" href="https://tmuxai.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/804"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[AI-Powered, Non-Intrusive Terminal Assistant

TmuxAI is a non-intrusive terminal assistant that works alongside you in a tmux window. TmuxAI&amp;#039;s design philosophy mirrors the way humans collaborate at the terminal. Just as a colleague sitting next to you, TmuxAI observes your screen, understand context from what&amp;#039;s visible, and helps accordingly. 

- [TmuxAI @ GitHub](https://github.com/alvinunreal/tmuxai).]]>
            </summary>
            <updated>2025-08-28T18:11:23+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/810</id>
            <title type="text"><![CDATA[Magnitude]]></title>
            <link rel="alternate" href="https://magnitude.run/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/810"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Open source, AI-native testing framework for web apps.

End-to-end testing framework powered by visual AI agents that see your interface and adapt to any changes in it.

- [Magnitude @ GitHub](https://github.com/magnitudedev/magnitude).]]>
            </summary>
            <updated>2025-08-28T18:12:23+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/846</id>
            <title type="text"><![CDATA[c/ua]]></title>
            <link rel="alternate" href="https://www.trycua.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/846"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[macOS &amp;amp; Linux Containers for Computer-Use AI Agents on Apple Silicon.
Run Docker Containers for Computer-Use AI Agents on Apple Silicon.

TL;DR: c/ua (pronounced &amp;quot;koo-ah&amp;quot;, short for Computer-Use Agent) is a framework that enables AI agents to control full operating systems within high-performance, lightweight virtual containers. It delivers up to 97% native speed on Apple Silicon and works with any vision language models.

- [c/ua @ GitHub](https://github.com/trycua/cua).]]>
            </summary>
            <updated>2025-08-28T18:18:30+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/849</id>
            <title type="text"><![CDATA[Index]]></title>
            <link rel="alternate" href="https://github.com/lmnr-ai/index" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/849"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Open-Source Browser Agent for autonomously performing complex tasks on the web]]>
            </summary>
            <updated>2025-08-28T18:19:25+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/881</id>
            <title type="text"><![CDATA[RowBoat Labs]]></title>
            <link rel="alternate" href="https://www.rowboatlabs.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/881"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[AI-powered multi-agent builder.
Let AI build multi-agent systems for you Build with Agents SDK.
Connect MCP tools. Open-source.

- [RowBoat @ GitHub](https://github.com/rowboatlabs/rowboat).]]>
            </summary>
            <updated>2025-08-28T18:24:31+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/891</id>
            <title type="text"><![CDATA[Cline]]></title>
            <link rel="alternate" href="https://cline.bot/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/891"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[AI Autonomous Coding Agent for VS Code.

 Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way. 

- [Cline @ GitHub](https://github.com/cline/cline).

Related contents:

- [Épisode \#108 - Les news web dev pour Mars 2025 RC2 @ Double Slash :fr:](https://double-slash.dev/podcasts/news-mars-rc2/).
- [Using Skills with Cline @ Data Science Collective](https://medium.com/data-science-collective/using-skills-with-cline-3acf2e289a7c).]]>
            </summary>
            <updated>2026-01-15T07:46:08+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/893</id>
            <title type="text"><![CDATA[Awesome MCP Servers]]></title>
            <link rel="alternate" href="https://glama.ai/mcp/servers" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/893"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Open-Source MCP servers

Production-ready and experimental MCP servers that extend AI capabilities through file access, database connections, API integrations, and other contextual services.

- [Awesome MCP Servers @ GitHub](https://github.com/punkpeye/awesome-mcp-servers).

Related contents:

- [Épisode \#108 - Les news web dev pour Mars 2025 RC2 @ Double Slash :fr:](https://double-slash.dev/podcasts/news-mars-rc2/).]]>
            </summary>
            <updated>2025-08-28T18:26:34+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/894</id>
            <title type="text"><![CDATA[Neon MCP Server]]></title>
            <link rel="alternate" href="https://github.com/neondatabase-labs/mcp-server-neon" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/894"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[MCP server for interacting with Neon Management API and databases.

Related contents:

- [Using Windsurf Cascade and Neon MCP for Agent-Driven Database Interaction @ Neon](https://neon.tech/blog/cascade-and-neon-mcp).]]>
            </summary>
            <updated>2025-08-28T18:26:35+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/899</id>
            <title type="text"><![CDATA[MCP Containers]]></title>
            <link rel="alternate" href="https://metorial.com/mcp/containers" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/899"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Containerized versions of hundreds of MCP servers 📡 🧠 

While experimenting with Model Context Protocol (MCP) servers, we found that setting them up could be a bit tedious and time-consuming. To simplify the process, we created containerized versions of these servers—making it quick, easy, and secure for anyone to get started.

- [MCP Containers @ GitHub](https://github.com/metorial/mcp-containers).]]>
            </summary>
            <updated>2025-08-28T18:27:31+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/906</id>
            <title type="text"><![CDATA[sidekick-cli]]></title>
            <link rel="alternate" href="https://github.com/geekforbrains/sidekick-cli" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/906"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Your agentic CLI developer.

Sidekick is an agentic CLI-based AI tool inspired by Claude Code, Copilot, Windsurf and Cursor. It&amp;#039;s meant to be an open source alternative to these tools, providing a similar experience but with the flexibility of using different LLM providers while keeping the agentic workflow.]]>
            </summary>
            <updated>2025-08-28T18:28:32+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/912</id>
            <title type="text"><![CDATA[Pocket Flow]]></title>
            <link rel="alternate" href="https://the-pocket.github.io/PocketFlow/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/912"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A 100-line minimalist LLM framework for Agents, Task Decomposition, RAG, etc.

- [Pocket Flow @ GitHub](https://github.com/The-Pocket/PocketFlow).

Related contents:

- [Turns Codebase into Easy Tutorial with AI @ GitHub](https://github.com/The-Pocket/Tutorial-Codebase-Knowledge).]]>
            </summary>
            <updated>2025-08-28T18:30:39+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/921</id>
            <title type="text"><![CDATA[React Agent Hooks]]></title>
            <link rel="alternate" href="https://github.com/chuanqisun/react-agent-hooks" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/921"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Turn React hooks into LLM tools]]>
            </summary>
            <updated>2025-08-28T18:31:32+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/923</id>
            <title type="text"><![CDATA[A practical guide to building agents :pdf:]]></title>
            <link rel="alternate" href="https://cdn.openai.com/business-guides-and-resources/a-practical-guide-to-building-agents.pdf" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/923"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Agents are AI systems that can perform workflows on users&amp;#039; behalf with a high degree of independence. This guide, designed for product and engineering teams, explores how to build agents with frameworks for identifying promise use cases, clear patterns for designing agent logic and orchestration, and best practices to ensure agents run safely, predictably, and effectively. It provides the foundational knowledge needed to confidently start building agents. Building reliable agents means starting with strong foundations - start small, validate with real users, and grow capabilities over time.]]>
            </summary>
            <updated>2025-08-28T18:31:33+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/927</id>
            <title type="text"><![CDATA[Codex CLI]]></title>
            <link rel="alternate" href="https://github.com/openai/codex" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/927"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Lightweight coding agent that runs in your terminal.

Codex CLI is built for developers who already live in the terminal and want ChatGPT‑level reasoning plus the power to actually run code, manipulate files, and iterate – all under version control. In short, it’s chat‑driven development that understands and executes your repo.]]>
            </summary>
            <updated>2025-08-28T18:32:32+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/928</id>
            <title type="text"><![CDATA[12 Factor Agents]]></title>
            <link rel="alternate" href="https://github.com/humanlayer/12-factor-agents" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/928"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Principles for building reliable LLM applications.

What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?]]>
            </summary>
            <updated>2025-08-28T18:32:33+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/929</id>
            <title type="text"><![CDATA[ActorCore]]></title>
            <link rel="alternate" href="https://actorcore.org/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/929"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[🎭 Stateful Serverless That Runs Anywhere. The easiest way to build stateful, AI agent, collaborative, or local-first applications. Deploy to Rivet, Cloudflare, Bun, Node.js, and more. 

ActorCore is a framework for building stateful, scalable, realtime backend applications. Whether you’re building multiplayer games, collaborative apps, AI agent backends, or any stateful service, ActorCore provides the tools and patterns to simplify your architecture.

- [ActorCore @ GitHub](https://github.com/rivet-gg/actor-core).]]>
            </summary>
            <updated>2025-08-28T18:32:34+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/937</id>
            <title type="text"><![CDATA[MCP-Shield]]></title>
            <link rel="alternate" href="https://github.com/riseandignite/mcp-shield" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/937"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Security scanner for MCP servers

MCP-Shield scans your installed MCP (Model Context Protocol) servers and detects vulnerabilities like tool poisoning attacks, exfiltration channels and cross-origin escalations.]]>
            </summary>
            <updated>2025-08-28T18:34:38+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/952</id>
            <title type="text"><![CDATA[Claude Code]]></title>
            <link rel="alternate" href="https://www.anthropic.com/claude-code" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/952"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Claude Code is Anthropic’s new agentic coding tool. A command-line companion that can read, edit, and manage your projects through natural language prompts. It integrates directly into your development environment, removing friction and helping you focus on what matters most: writing great code.

Related contents:

- [Poking Around Claude Code @ Han, Not Solo](https://leehanchung.github.io/blogs/2025/03/07/claude-code/).
- [What makes Claude Code so damn good (and how to recreate that magic in your agent)!? @ minusx](https://minusx.ai/blog/decoding-claude-code/).
- [Claude Code: Best practices for agentic coding @ Engineering at Anthropic](https://www.anthropic.com/engineering/claude-code-best-practices).
- [Agentic Coding Recommendations @ Armin Ronacher&amp;#039;s Thoughts and Writings](https://lucumr.pocoo.org/2025/6/12/agentic-coding/).
- [Quand Claude Code pilote votre terminal... @ Korben :fr:](https://korben.info/quand-claude-code-pilote-votre-terminal.html).
- [Turning Claude Code Into My Best Design Partner @ Between the Prompts](https://betweentheprompts.com/design-partner/).
- [Using Claude Code to modernize a 25-year-old kernel driver @ Dmitry Brant](https://dmitrybrant.com/2025/09/07/using-claude-code-to-modernize-a-25-year-old-kernel-driver).
- [The babysitter problem @ chrisbeckman.dev](https://chrisbeckman.dev/posts/the-babysitter-problem).
- [Claude Skills are awesome, maybe a bigger deal than MCP @ Simon Willison’s Weblog](https://simonwillison.net/2025/Oct/16/claude-skills/).
- [Mastering Claude Code in 30 minutes @ Anthropic&amp;#039;s YouTube](https://www.youtube.com/watch?v=6eBSHbLKuN0).]]>
            </summary>
            <updated>2026-04-28T07:42:51+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/954</id>
            <title type="text"><![CDATA[awesome-ai-system-prompts]]></title>
            <link rel="alternate" href="https://github.com/dontriskit/awesome-ai-system-prompts" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/954"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Crafting Effective Prompts for Agentic AI Systems: Patterns and Practices.

 🧠 Curated collection of system prompts for top AI tools. Perfect for AI agent builders and prompt engineers. Incuding: ChatGPT, Claude, Perplexity, Manus, Claude-Code, Loveable, v0, Grok, same new, windsurf, notion, and MetaAI.]]>
            </summary>
            <updated>2025-08-28T18:36:38+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1001</id>
            <title type="text"><![CDATA[Agent2Agent Protocol (A2A)]]></title>
            <link rel="alternate" href="https://google.github.io/A2A/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1001"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[An open protocol enabling communication and interoperability between opaque agentic applications.

One of the biggest challenges in enterprise AI adoption is getting agents built on different frameworks and vendors to work together. That’s why we created an open Agent2Agent (A2A) protocol, a collaborative way to help agents across different ecosystems communicate with each other.

- [Agent2Agent Protocol (A2A) @ GitHub](https://github.com/google/A2A).

Related contents:

- [Announcing the Agent2Agent Protocol (A2A) @ Google for Developers](https://developers.googleblog.com/en/a2a-a-new-era-of-agent-interoperability/).
- [MCP vs. A2A: Friends or Foes? @ SwirlAI Newsletter](https://www.newsletter.swirlai.com/p/mcp-vs-a2a-friends-or-foes).]]>
            </summary>
            <updated>2025-08-28T18:44:39+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1009</id>
            <title type="text"><![CDATA[🐫 CAMEL]]></title>
            <link rel="alternate" href="https://www.camel-ai.org/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1009"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The first and the best multi-agent framework. Finding the Scaling Law of Agents

Building Multi-Agent Systems for Task Automation.

 🐫 CAMEL is an open-source community dedicated to finding the scaling laws of agents. We believe that studying these agents on a large scale offers valuable insights into their behaviors, capabilities, and potential risks. To facilitate research in this field, we implement and support various types of agents, tasks, prompts, models, and simulated environments.

CAMEL emerges as the earliest LLM-based multi-agent framework, and is now a generic framework to build and use LLM-based agents for real-world task solving. We believe that studying these agents on a large scale offers valuable insights into their behaviors, capabilities, and potential risks. To facilitate research in this field, we implement and support various types of agents, tasks, prompts, models, and simulated environments.

- [🐫 CAMEL @ GitHub](https://github.com/camel-ai/camel).
- [🐫 CAMEL&amp;#039;s documentation](https://docs.camel-ai.org/).]]>
            </summary>
            <updated>2025-08-28T18:46:41+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1011</id>
            <title type="text"><![CDATA[Gemini API]]></title>
            <link rel="alternate" href="https://ai.google.dev/gemini-api/docs?hl=en" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1011"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Google AI for Developers

- [Gemini API Cookbook @ GitHub](https://github.com/google-gemini/cookbook).]]>
            </summary>
            <updated>2025-08-28T18:46:42+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1018</id>
            <title type="text"><![CDATA[Browser MCP]]></title>
            <link rel="alternate" href="https://browsermcp.io/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1018"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[MCP server for your browser.

 Browser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser.

If you want to automate actions on a website, like repeatedly fill out a form, you normally can&amp;#039;t do it with AI apps like Cursor or Claude because they don&amp;#039;t have access to a web browser. With Browser MCP, you can connect AI apps to your browser so they can automate tasks on your behalf.

- [Browser MCP @ GitHub](https://github.com/browsermcp/mcp).]]>
            </summary>
            <updated>2025-08-28T18:46:44+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1062</id>
            <title type="text"><![CDATA[GitMCP]]></title>
            <link rel="alternate" href="https://gitmcp.io/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1062"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Instantly create a Remote MCP server for any GitHub project.

GitMCP is a free, open-source service that seamlessly transforms any GitHub project into a remote Model Context Protocol (MCP) endpoint, enabling AI assistants to access and understand the project&amp;#039;s documentation effortlessly.

- [GitMCP @ GitHub](https://github.com/idosal/git-mcp).]]>
            </summary>
            <updated>2025-08-28T18:54:55+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1063</id>
            <title type="text"><![CDATA[AWS MCP Servers]]></title>
            <link rel="alternate" href="https://awslabs.github.io/mcp/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1063"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[specialized MCP servers that bring AWS best practices directly to your development workflow .

- [AWS MCP Servers @ GitHub](https://github.com/awslabs/mcp).]]>
            </summary>
            <updated>2025-08-28T18:54:56+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1079</id>
            <title type="text"><![CDATA[Fast MCP 🚀]]></title>
            <link rel="alternate" href="https://github.com/yjacquin/fast-mcp" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1079"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A Ruby Implementation of the Model Context Protocol.

Connect AI models to your Ruby applications with ease
No complex protocols, no integration headaches, no compatibility issues – just beautiful, expressive Ruby code.]]>
            </summary>
            <updated>2025-08-28T18:56:46+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1087</id>
            <title type="text"><![CDATA[airflow-ai-sdk]]></title>
            <link rel="alternate" href="https://github.com/astronomer/airflow-ai-sdk?tab=readme-ov-file" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1087"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[An SDK for working with LLMs and AI Agents from Apache Airflow, based on Pydantic AI.
 
It allows users to call LLMs and orchestrate agent calls directly within their Airflow pipelines using decorator-based tasks. The SDK leverages the familiar Airflow @task syntax with extensions like @task.llm, @task.llm_branch, and @task.agent.]]>
            </summary>
            <updated>2025-08-28T18:58:50+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1095</id>
            <title type="text"><![CDATA[Langtrace]]></title>
            <link rel="alternate" href="https://www.langtrace.ai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1095"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Transform Al Prototypes into Enterprise-Grade Products.

Langtrace is an Open Source Observability and Evaluations Platform for Al Agents.

- [Langtrace @ GitHub](https://github.com/Scale3-Labs/langtrace).

Related contents:

- [Tracing a RAG based Chatbot with Elastic Distributions of OpenTelemetry and Langtrace @ elastic observability labs](https://www.elastic.co/observability-labs/blog/openai-tracing-langtrace-elastic).]]>
            </summary>
            <updated>2025-08-28T18:58:54+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1101</id>
            <title type="text"><![CDATA[PG-MCP]]></title>
            <link rel="alternate" href="https://github.com/stuzero/pg-mcp" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1101"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[PostgreSQL Model Context Protocol (PG-MCP) Server.

A Model Context Protocol (MCP) server for PostgreSQL databases with enhanced capabilities for AI agents.]]>
            </summary>
            <updated>2025-08-28T18:59:48+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1162</id>
            <title type="text"><![CDATA[Playwright MCP]]></title>
            <link rel="alternate" href="https://github.com/microsoft/playwright-mcp" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1162"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Playwright Tools for MCP.

A Model Context Protocol (MCP) server that provides browser automation capabilities using Playwright. This server enables LLMs to interact with web pages through structured accessibility snapshots, bypassing the need for screenshots or visually-tuned models.

Related contents:

- [Guide détaillé du serveur Playwright MCP @ bright data :fr:](https://brightdata.fr/blog/ai/playwright-mcp-server).
- [\#346.src - IA &amp;amp; DevX: Code assisté, valeur humaine préservée avec Jocelyn N&amp;#039;takpe @ \&amp;lt;ifttd&amp;gt;](https://www.ifttd.io/episodes/ia-devx).]]>
            </summary>
            <updated>2026-03-22T18:14:52+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1171</id>
            <title type="text"><![CDATA[LangGraph]]></title>
            <link rel="alternate" href="https://www.langchain.com/langgraph" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1171"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Balance agent control with agency.  Build resilient language agents as graphs. 

Gain control with LangGraph to design agents that reliably handle complex tasks. Build and scale agentic applications with LangGraph Platform.

LangGraph — used by Replit, Uber, LinkedIn, GitLab and more — is a low-level orchestration framework for building controllable agents. While langchain provides integrations and composable components to streamline LLM application development, the LangGraph library enables agent orchestration — offering customizable architectures, long-term memory, and human-in-the-loop to reliably handle complex tasks.

- [LangGraph @ GitHub](https://github.com/langchain-ai/langgraph).

Related contents:

- [Why we chose LangGraph to build our coding agent @  qodo](https://www.qodo.ai/blog/why-we-chose-langgraph-to-build-our-coding-agent/).
- [LangGraph for complex workflows @ surma.dev](https://surma.dev/things/langgraph/).
- [LangChain, LangGraph Flaws Expose Files, Secrets, Databases in Widely Used AI Frameworks @ The Hacker News](https://thehackernews.com/2026/03/langchain-langgraph-flaws-expose-files.html).]]>
            </summary>
            <updated>2026-03-30T18:57:36+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1193</id>
            <title type="text"><![CDATA[Desktop Commander MCP]]></title>
            <link rel="alternate" href="https://github.com/wonderwhy-er/ClaudeDesktopCommander" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1193"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[This is MCP server for Claude that gives it terminal control, file system search and diff file editing capabilities.

This is server that allows Claude desktop app to execute long-running terminal commands on your computer and manage processes through Model Context Protocol (MCP) + Built on top of MCP Filesystem Server to provide additional search and replace file editing capabilities .]]>
            </summary>
            <updated>2025-08-28T19:15:01+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1196</id>
            <title type="text"><![CDATA[Fleur MCP App Store]]></title>
            <link rel="alternate" href="https://www.fleurmcp.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1196"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Fleur is the app store for Claude.
 The easiest way to discover and install MCPs.

Fleur is a desktop application that serves as an app marketplace for MCPs. It allows you to discover, install, and manage apps that extend the functionality of Claude Desktop and Cursor.

All without having to use a command line. Fleur is made for non-technical users in mind, but is open-source and extensible so developers can make it their own.

- [Fleur @ GitHub](https://github.com/fleuristes/fleur).

Related contents:

- [Fleur MCP - Comment donner des super-pouvoirs à Claude @ Korben :fr:](https://korben.info/fleur-mcp-comment-donner-super-pouvoirs-claude.html).]]>
            </summary>
            <updated>2025-08-28T19:15:03+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1223</id>
            <title type="text"><![CDATA[Fetcher MCP]]></title>
            <link rel="alternate" href="https://github.com/jae-jae/fetcher-mcp" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1223"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[MCP server for fetch web page content using Playwright headless browser.]]>
            </summary>
            <updated>2025-08-28T19:19:58+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1236</id>
            <title type="text"><![CDATA[codemcp]]></title>
            <link rel="alternate" href="https://github.com/ezyang/codemcp" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1236"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Coding assistant MCP for Claude Desktop.

Make Claude Desktop a pair programming assistant by installing codemcp. With it, you can directly ask Claude to implement features, fix bugs and do refactors on a codebase on your computer; Claude will directly edit files and run tests. Say goodbye to copying code in and out of Claude&amp;#039;s chat window!]]>
            </summary>
            <updated>2025-08-28T19:23:01+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1237</id>
            <title type="text"><![CDATA[Cloudflare MCP Server]]></title>
            <link rel="alternate" href="https://github.com/cloudflare/mcp-server-cloudflare" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1237"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Model Context Protocol (MCP) is a new, standardized protocol for managing context between large language models (LLMs) and external systems. In this repository, we provide an installer as well as an MCP Server for Cloudflare&amp;#039;s API.

This lets you use Claude Desktop, or any MCP Client, to use natural language to accomplish things on your Cloudflare account]]>
            </summary>
            <updated>2025-08-28T19:23:02+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1245</id>
            <title type="text"><![CDATA[kagent]]></title>
            <link rel="alternate" href="https://kagent.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1245"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Bringing Agentic AI to cloud native.

An open-source framework for DevOps and platform engineers to run AI agents in Kubernetes, automating complex operations and troubleshooting tasks.

- [kagent @ GitHub](https://github.com/kagent-dev/kagent).

Related contents:

- [Kagent: Bringing Agentic AI to Cloud Native @ Cloud Native computing foundation](https://www.cncf.io/blog/2025/04/15/kagent-bringing-agentic-ai-to-cloud-native/).
- [Bringing NemoClaw Support to kagent @ solo.io](https://www.solo.io/blog/kagent-nemoclaw).]]>
            </summary>
            <updated>2026-05-14T18:56:57+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1334</id>
            <title type="text"><![CDATA[Evolving Agents Framework]]></title>
            <link rel="alternate" href="https://github.com/matiasmolinas/evolving-agents" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1334"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Evolving agents is a production-grade environment for orchestrating, evolving, and managing AI agents.

A production-grade framework for creating, managing, and evolving AI agents with intelligent agent-to-agent communication. The framework enables you to build collaborative agent ecosystems that can semantically understand requirements, evolve based on past experiences, and communicate effectively to solve complex tasks.]]>
            </summary>
            <updated>2025-08-28T19:39:09+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1335</id>
            <title type="text"><![CDATA[Building an Agentic System]]></title>
            <link rel="alternate" href="https://gerred.github.io/building-an-agentic-system/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1335"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[An in-depth book and reference on building agentic systems like Claude Code.
A deep-dive guide into architecture patterns for building responsive, reliable AI coding agents.

There&amp;#039;s been a lot of asking about how Claude Code works under the hood. Usually, people see the prompts, but they don&amp;#039;t see how it all comes together. This is that book. All of the systems, tools, and commands that go into building one of these.

A practical deep dive and code review into how to build a self-driving coding agent, execution engine, tools and commands. Rather than the prompts and AI engineering, this is the systems and design decisions that go into making agents that are real-time, self-corrective, and useful for productive work.

- [Building an Agentic System @ GitHub](https://github.com/gerred/building-an-agentic-system).]]>
            </summary>
            <updated>2025-08-28T19:39:10+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1338</id>
            <title type="text"><![CDATA[Letta]]></title>
            <link rel="alternate" href="https://www.letta.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1338"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The Platform for Building Stateful Agents.
Build agents with infinite context and human-like memory, that can learn from data and improve with experience.
 Letta (formerly MemGPT) is a framework for creating LLM services with memory. 

👾 Letta is an open source framework for building stateful LLM applications. You can use Letta to build stateful agents with advanced reasoning capabilities and transparent long-term memory. The Letta framework is white box and model-agnostic.

- [Letta @ GitHub](https://github.com/letta-ai/letta).
- [Letta documentation](https://docs.letta.com/).

Related contents:

- [Letta Filesystem @ Letta documentation](https://docs.letta.com/guides/agents/filesystem).]]>
            </summary>
            <updated>2025-10-17T05:38:21+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1342</id>
            <title type="text"><![CDATA[CAMEL-AI Framework]]></title>
            <link rel="alternate" href="https://camel-ai.org/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1342"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Finding the Scaling Laws of Agents. The first and the best multi-agent framework.

 🐫 CAMEL is an open-source community dedicated to finding the scaling laws of agents. We believe that studying these agents on a large scale offers valuable insights into their behaviors, capabilities, and potential risks. To facilitate research in this field, we implement and support various types of agents, tasks, prompts, models, and simulated environments.

The framework enables multi-agent systems to continuously evolve by generating data and interacting with environments. This evolution can be driven by reinforcement learning with verifiable rewards or supervised learning.

- [CAMEL-AI @ GitHub](https://github.com/camel-ai/camel).]]>
            </summary>
            <updated>2025-08-28T19:40:07+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1361</id>
            <title type="text"><![CDATA[Arch Gateway]]></title>
            <link rel="alternate" href="https://www.archgw.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1361"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Go beyond nascent AI demos. The intelligent AI-native gateway for prompts and agentic apps.

Effortlessly build AI apps that can answer questions and help users get things done. Arch is the AI-native proxy that handles the pesky heavy-lifting so that you can move faster in building agentic apps, prevent harmful outcomes, and rapidly incorporate latest models. 

 AI-native (edge and LLM) proxy for agents. Move faster by letting Arch handle the pesky heavy lifting in building agentic apps -- ⚡️ query understanding and routing, seamless integration of prompts with tools, and unified access and observability of LLMs. Built by the contributors of Envoy proxy. 

- [Arch Gateway @ GitHub](https://github.com/katanemo/archgw).]]>
            </summary>
            <updated>2025-08-28T19:43:12+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1369</id>
            <title type="text"><![CDATA[agents.json]]></title>
            <link rel="alternate" href="https://docs.wild-card.ai/agentsjson/introduction" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1369"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The agents.json Specification is an open specification that formally describes contracts for API and agent interactions, built on top of the OpenAPI standard.

- [agents.json @ GitHub](https://github.com/wild-card-ai/agents-json).]]>
            </summary>
            <updated>2025-08-28T19:44:10+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1508</id>
            <title type="text"><![CDATA[GenSX]]></title>
            <link rel="alternate" href="https://www.gensx.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1508"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The TypeScript framework for agents &amp;amp; workflows with react-like components. Lightning fast dev loop. Easy to learn. Easy to extend. 

Build complex AI applications with React-like components.
GenSX is a simple typescript framework for building agents and workflows with reusable React-like components.
GenSX takes a lot of inspiration from React, but the programming model is very different - it’s a Node.js framework designed for data flow.

- [GenSX @ GitHub](https://github.com/gensx-inc/gensx).]]>
            </summary>
            <updated>2025-08-28T20:07:28+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1602</id>
            <title type="text"><![CDATA[open Deep Research]]></title>
            <link rel="alternate" href="https://m-ric-open-deep-research.hf.space/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1602"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[OpenAI just published Deep Research, a very nice assistant that can perform deep searches on the web to answer user questions.

However, their agent has a huge downside: it&amp;#039;s not open. So we&amp;#039;ve started a 24-hour rush to replicate and open-source it. Our resulting open-Deep-Research agent took the #1 rank of any open submission on the GAIA leaderboard! ✨

- [open Deep Research @ HuggingFace smolagents&amp;#039; GitHub](https://github.com/huggingface/smolagents/tree/main/examples/open_deep_research).

Related contents:

- [Open-source DeepResearch – Freeing our search agents @ Hugging Face](https://huggingface.co/blog/open-deep-research).]]>
            </summary>
            <updated>2025-08-28T20:23:35+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1708</id>
            <title type="text"><![CDATA[Browser Use]]></title>
            <link rel="alternate" href="https://browser-use.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1708"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Enable AI to control your browser. Make websites accessible for AI agents.

We make websites accessible for AI agents by extracting all interactive elements, so agents can focus on what makes their beer taste better.

- [Browser Use @ GitHub](https://github.com/browser-use/browser-use).

Related contents:

- [Browser Use, one of the tools powering Manus, is also going viral @ TechCrunch](https://techcrunch.com/2025/03/12/browser-use-one-of-the-tools-powering-manus-is-also-going-viral/).
- [Episode 616: From Boston to bootc @ Linux Unplugged](https://linuxunplugged.com/616).]]>
            </summary>
            <updated>2026-03-28T08:18:51+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1748</id>
            <title type="text"><![CDATA[🦜🕸️LangGraph]]></title>
            <link rel="alternate" href="https://langchain-ai.github.io/langgraph/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1748"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[LangGraph is a library for building stateful, multi-actor applications with LLMs, used to create agent and multi-agent workflows.

- [🦜🕸️LangGraph @ GitHub](https://github.com/langchain-ai/langgraph).

Related contents:

- [Building effective agents @ Anthropic](https://www.anthropic.com/research/building-effective-agents).]]>
            </summary>
            <updated>2025-08-28T20:47:51+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1749</id>
            <title type="text"><![CDATA[Vellum AI]]></title>
            <link rel="alternate" href="https://www.vellum.ai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1749"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Build and ship AI products on a single, collaborative platform

Take AI products from early-stage ideas to production-grade features with tooling for experimentation, evaluation, deployment, monitoring, and collaboration.

Related contents:

- [Building effective agents @ Anthropic](https://www.anthropic.com/research/building-effective-agents).]]>
            </summary>
            <updated>2025-08-28T20:47:52+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1750</id>
            <title type="text"><![CDATA[Rivet]]></title>
            <link rel="alternate" href="https://rivet.ironcladapp.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1750"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The open-source visual AI programming environment and TypeScript library.

Rivet, the IDE for creating complex AI agents and prompt chaining, and embedding it in your application. 

- [Rivet @ GitHub](https://github.com/Ironclad/rivet).

Related contents:

- [Building effective agents @ Anthropic](https://www.anthropic.com/research/building-effective-agents).]]>
            </summary>
            <updated>2025-08-28T20:47:52+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1751</id>
            <title type="text"><![CDATA[Amazon Bedrock Agents]]></title>
            <link rel="alternate" href="https://aws.amazon.com/bedrock/agents/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1751"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Enable generative AI applications to automate multistep tasks by seamlessly connecting with company systems, APIs, and data sources.

Related contents:

- [Building effective agents @ Anthropic](https://www.anthropic.com/research/building-effective-agents).]]>
            </summary>
            <updated>2025-08-28T20:47:53+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1759</id>
            <title type="text"><![CDATA[codename goose]]></title>
            <link rel="alternate" href="https://block.github.io/goose/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1759"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Your on-machine AI agent, automating engineering tasks seamlessly.
an open-source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM.

- [codename goose @ GitHub](https://github.com/block/goose).

Related contents:

- [Introducing codename goose @ codename goose blog](https://block.github.io/goose/blog/2025/01/28/introducing-codename-goose/).]]>
            </summary>
            <updated>2025-08-28T20:49:47+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1779</id>
            <title type="text"><![CDATA[Haystack]]></title>
            <link rel="alternate" href="https://haystack.deepset.ai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1779"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The Production-Ready Open Source AI Framework.

 AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it&amp;#039;s best suited for building RAG, question answering, semantic search or conversational agent chatbots. 

- [Haystack @ GitHub](https://github.com/deepset-ai/haystack).]]>
            </summary>
            <updated>2025-08-28T20:52:51+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1898</id>
            <title type="text"><![CDATA[Agent Recipes]]></title>
            <link rel="alternate" href="https://www.agentrecipes.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1898"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Explore Agent Recipes

Explore common agent recipes with ready to copy code to improve your LLM applications. 

Related contents:

- [Building effective agents @ Anthropic](https://www.anthropic.com/research/building-effective-agents).]]>
            </summary>
            <updated>2025-08-28T21:13:01+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1927</id>
            <title type="text"><![CDATA[Realtime API Agents Demo]]></title>
            <link rel="alternate" href="https://github.com/openai/openai-realtime-agents" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1927"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[This is a simple demonstration of more advanced, agentic patterns built on top of the Realtime API. - openai/openai-realtime-agents]]>
            </summary>
            <updated>2025-08-28T21:17:07+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/1988</id>
            <title type="text"><![CDATA[LackSynth]]></title>
            <link rel="alternate" href="https://github.com/aielte-research/HackSynth" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/1988"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[LLM Agent and Evaluation Framework for Autonomous Penetration Testing.

We introduce HackSynth, a novel Large Language Model (LLM)-based agent capable of autonomous penetration testing. HackSynth&amp;#039;s dual-module architecture includes a Planner and a Summarizer, which enable it to generate commands and process feedback iteratively. To benchmark HackSynth, we propose two new Capture The Flag (CTF)-based benchmark sets utilizing the popular platforms PicoCTF and OverTheWire. These benchmarks include two hundred challenges across diverse domains and difficulties, providing a standardized framework for evaluating LLM-based penetration testing agents.]]>
            </summary>
            <updated>2025-08-28T21:28:14+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/2198</id>
            <title type="text"><![CDATA[🤗 smolagents]]></title>
            <link rel="alternate" href="https://github.com/huggingface/smolagents" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/2198"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[🤗 smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents.]]>
            </summary>
            <updated>2025-08-28T22:02:31+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/2219</id>
            <title type="text"><![CDATA[Browserbase]]></title>
            <link rel="alternate" href="https://www.browserbase.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/2219"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A web browser for AI agents &amp;amp; applications.
An AI web browsing framework focused on simplicity and extensibility. 

- [🤘 Stagehand @ GitHub](https://github.com/browserbase/stagehand).]]>
            </summary>
            <updated>2025-08-28T22:06:31+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/2289</id>
            <title type="text"><![CDATA[Flowise]]></title>
            <link rel="alternate" href="https://flowiseai.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/2289"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Low code LLM Apps Builder. Build LLM Apps Easily.

Open source low-code tool for developers to build customized LLM orchestration flow &amp;amp; AI agents.

- [Flowise @ GitHub](https://github.com/FlowiseAI/Flowise).

Related contents:

- [CVE-2024–8182 : Accidental Discovery of an Unauthenticated DoS @ Tenable TechBlog&amp;#039;s Medium](https://medium.com/tenable-techblog/cve-2024-8182-accidental-discovery-of-an-unauthenticated-dos-1d89947a09a4).]]>
            </summary>
            <updated>2025-08-28T22:17:40+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/2294</id>
            <title type="text"><![CDATA[AmphiPod]]></title>
            <link rel="alternate" href="https://github.com/sea-monkeys/amphipod" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/2294"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[AmphiPod is a lightweight, HTTP-based Model Context Protocol (MCP) server implementation written in Go. It simplifies the integration of AI tools by providing an HTTP interface to the MCP specification and executing tools through WebAssembly plugins.]]>
            </summary>
            <updated>2025-08-28T22:18:41+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/2311</id>
            <title type="text"><![CDATA[PydanticAI]]></title>
            <link rel="alternate" href="https://ai.pydantic.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/2311"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Agent Framework / shim to use Pydantic with LLMs.

PydanticAI is a Python Agent Framework designed to make it less painful to build production grade applications with Generative AI.

- [PydanticAI @ GitHub](https://github.com/pydantic/pydantic-ai).

Related contents:

- [PydanticAI: A New Python Framework for Streamlined Generative AI Development @ InfoQ](https://www.infoq.com/news/2024/12/pydanticai-framework-gen-ai/).
- [Building your own CLI Coding Agent with Pydantic-AI @ martinFowler.com](https://martinfowler.com/articles/build-own-coding-agent.html).]]>
            </summary>
            <updated>2025-09-09T15:34:00+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/2451</id>
            <title type="text"><![CDATA[BrowserGym]]></title>
            <link rel="alternate" href="https://github.com/ServiceNow/BrowserGym" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/2451"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[🌎💪 BrowserGym, a Gym environment for web task automation.

BrowserGym is meant to provide an open, easy-to-use and extensible framework to accelerate the field of web agent research. It is not meant to be a consumer product. Use with caution!]]>
            </summary>
            <updated>2025-08-28T22:45:04+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/2489</id>
            <title type="text"><![CDATA[LaVague]]></title>
            <link rel="alternate" href="https://www.lavague.ai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/2489"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Open-source framework for building Web Agents.
Build and deploy Web Agents in a few lines of code.

- [LaVague @ GitHub](https://github.com/lavague-ai/LaVague).
- [LaVague documentation](https://docs.lavague.ai/en/latest/).]]>
            </summary>
            <updated>2025-08-28T22:50:58+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/2490</id>
            <title type="text"><![CDATA[Wren AI]]></title>
            <link rel="alternate" href="https://getwren.ai/oss" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/2490"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Open-source sQL AI Agent. Text2SQL made Easy!

Wren AI is an open-source SQL AI Agent that empowers data, product, and business teams to access insights through AI chat, built-in well designed intuitive UI and UX, integrating seamlessly with tools like Excel and Google Sheets.

- [Wren AI @ GitHub](https://github.com/Canner/WrenAI).]]>
            </summary>
            <updated>2025-08-28T22:50:59+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/3278</id>
            <title type="text"><![CDATA[Swarm]]></title>
            <link rel="alternate" href="https://github.com/openai/swarm" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/3278"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

Related contents:

- [Don’t Build Multi-Agents @ Cognition](https://cognition.ai/blog/dont-build-multi-agents#principles-of-context-engineering).]]>
            </summary>
            <updated>2025-09-17T14:31:00+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/3424</id>
            <title type="text"><![CDATA[Crew AI]]></title>
            <link rel="alternate" href="https://www.crewai.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/3424"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks. 

- [Crew AI @ GitHub](https://github.com/crewAIInc/crewAI).

Related contents:

- [S5E8 - Votre téléphone vous ment (et c&amp;#039;est fascinant) @ Underscore_&amp;#039;s acast :fr:](https://shows.acast.com/micode-underscore/episodes/s5e8-votre-telephone-vous-ment-et-cest-fascinant).
- [Tour d&amp;#039;horizon des frameworks pour créer des applications basées sur les LLM @ Data-Crafting.io :fr:](https://datacrafting.substack.com/p/tour-dhorizon-des-frameworks-pour).]]>
            </summary>
            <updated>2025-08-29T01:27:01+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/3685</id>
            <title type="text"><![CDATA[Plandex]]></title>
            <link rel="alternate" href="https://plandex.ai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/3685"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[AI coding engine for complex tasks. Build complex software with AI.

An open source, terminal-based AI coding engine.
Designed for real-world tasks that span many files.

- [Plandex @ GitHub](https://github.com/plandex-ai/plandex).

Related contents:

- [Plandex – L’assistant qui dev @ Korben :fr:](https://korben.info/plandex-ia-developpeurs-productivite-code.html).]]>
            </summary>
            <updated>2025-08-29T02:10:23+00:00</updated>
        </entry>
    </feed>
