<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
    <title>multi-agent</title>
    <link rel="self" type="application/atom+xml" href="https://links.biapy.com/guest/tags/1653/feed"/>
    <updated>2026-09-21T15:27:52+00:00</updated>
    <id>https://links.biapy.com/guest/tags/1653/feed</id>
            <entry>
            <id>https://links.biapy.com/links/13937</id>
            <title type="text"><![CDATA[Ouroboros]]></title>
            <link rel="alternate" href="https://ouroboros.page/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13937"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[spec, run, verify AI coding work. Your coding agent writes the code. Ouroboros verifies the result.

Ouroboros manages the requirements, execution, evaluation, and records of AI coding work. It pins the spec before the run and verifies the result after it.

Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.

- [Ouroboros @ GitHub](https://github.com/Q00/ouroboros).]]>
            </summary>
            <updated>2026-09-17T13:11:06+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13928</id>
            <title type="text"><![CDATA[OpenResearch]]></title>
            <link rel="alternate" href="https://openresearch.sh/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13928"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Autoresearch on your machine

Start the local dashboard, then give each research direction its own agent. They work in parallel, in isolated worktrees, using your existing tools and compute.

To spin up remote compute while doing Autoresearch, use OpenResearch&amp;#039;s compute marketplace, which aggregates offerings from multiple providers.

- [OpenResearch @ GitHub](https://github.com/alphaXiv/OpenResearch).]]>
            </summary>
            <updated>2026-09-16T12:22:22+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13927</id>
            <title type="text"><![CDATA[Pizza Bot OSS]]></title>
            <link rel="alternate" href="https://github.com/pizza-bot-app/pizza-bot" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13927"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A local-first inbox for long-running AI agents, built with DeepAgents and LangGraph.

Pizza Bot is an inbox for long-running AI work. Start or schedule a task, return to your day, and let completed work collect in Unread while runs waiting for your decision collect in Action. Agents keep working when you navigate away or disconnect; the api-server process must remain running.]]>
            </summary>
            <updated>2026-09-16T12:21:00+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13926</id>
            <title type="text"><![CDATA[Ordewell]]></title>
            <link rel="alternate" href="https://ordewell.ai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13926"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[task orchestration for coding agents.
One goal. An ordered plan of agent tasks. Every runner, model and effort visible before you spend a token.

The planner reads your repo, asks about whatever you left vague, and hands back tasks you can rewrite — prompts, models, modes, dependencies, all of it. Then it runs one real coding-agent session per task, and completes a task only when that task&amp;#039;s marker shows up in the output. 

Multi-agent task orchestration for coding agents. Turn one goal into an ordered plan of tasks — each with its own runner, model and mode — then execute and verify the results.

- [Ordewell @ GitHub](https://github.com/ordewell/ordewell).]]>
            </summary>
            <updated>2026-09-16T12:19:52+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13925</id>
            <title type="text"><![CDATA[Zenith]]></title>
            <link rel="alternate" href="https://github.com/Intelligent-Internet/zenith" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13925"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[a continuous-improvement harness for long-running agent tasks. Turns Claude Code, Codex, or Hermes into a multi-agent mission orchestrator via MCP/ACP.

Zenith is an agent harness for work that may run for days or weeks, where the dominant failure mode is premature completion rather than inability to make progress. It runs a coding agent (Claude Code, Codex, or Hermes) as a multi-agent orchestrator over MCP/ACP: one orchestrator session reads task state each turn and decides whether to spawn workers and testers, register reusable skills, replan, or stop.]]>
            </summary>
            <updated>2026-09-15T19:42:40+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13903</id>
            <title type="text"><![CDATA[nightshift]]></title>
            <link rel="alternate" href="https://github.com/openslop/nightshift" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13903"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Your repo gets better while you sleep. Nightly agent jobs and PR review for any repo.

Nightshift is a helper that works at night.

It wakes up your coding agent. It gives the agent one small job. The agent looks at your code and does the job. If it finds something worth fixing, it opens a pull request for you to look at. Then it moves to the next job.]]>
            </summary>
            <updated>2026-09-14T06:32:17+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13829</id>
            <title type="text"><![CDATA[Buzz 🐝]]></title>
            <link rel="alternate" href="https://github.com/block/buzz" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13829"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A hive mind communication platform.
 
A workspace where humans and agents build together, on a relay you own. 

Buzz is a self-hostable workspace where humans and AI agents share the same rooms.

A Buzz community is the workspace a user reaches by URL. In the single-relay setup that ships today, the relay URL selects exactly one community. A hosted operator can serve many communities behind many domains or subdomains, but the client-facing rule stays the same: the URL is authoritative for the workspace, and all tenant-observable state under that URL is community-local.]]>
            </summary>
            <updated>2026-09-07T19:53:18+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13800</id>
            <title type="text"><![CDATA[OpenHands]]></title>
            <link rel="alternate" href="https://www.openhands.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13800"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The Open Platform for Cloud Coding Agents.

 The self-hosted developer control center for coding agents and automations.

Run OpenHands, Claude Code, Codex, Gemini, or any ACP-compatible agent across local, remote, and cloud backends. 

- [OpenHands @ GitHub](https://github.com/OpenHands/OpenHands).]]>
            </summary>
            <updated>2026-09-05T16:09:38+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13794</id>
            <title type="text"><![CDATA[warren]]></title>
            <link rel="alternate" href="https://app.warren.run/#/operations" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13794"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Run coding agents like infrastructure, not terminal sessions. Warren manages isolation, lifecycle, spend, recovery, and Git delivery on compute you control.

Warren runs agent harnesses as isolated, observable workloads on infrastructure you control. It owns the workspace, run lifecycle, spend limits, live events, intervention, recovery, and Git delivery.

- [warren @ GitHub](https://github.com/jayminwest/warren).]]>
            </summary>
            <updated>2026-09-05T08:44:20+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13754</id>
            <title type="text"><![CDATA[Open Executive]]></title>
            <link rel="alternate" href="https://openexec-ui-dev.fly.dev/signin?callbackUrl=%2F" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13754"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[AI-powered virtual executive team — a single coherent executive persona backed by 8 specialist Claude agents (FastAPI + Next.js).

- [Open Executive @ GitHub](https://github.com/SenteLabsAI/OpenExecutive).]]>
            </summary>
            <updated>2026-09-02T16:55:31+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13735</id>
            <title type="text"><![CDATA[Apache Maka]]></title>
            <link rel="alternate" href="https://maka.apposters.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13735"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Local-First AI Agent Workspace.

 A local-first Agent workspace built for real work. Maka inspects projects, runs tools under a sandbox boundary, and records model messages and tool calls as recoverable execution facts — on your machine, through one Runtime Host. 

- [Apache Maka @ GitHub](https://github.com/apache/maka).]]>
            </summary>
            <updated>2026-08-31T09:09:23+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13734</id>
            <title type="text"><![CDATA[Proliferate]]></title>
            <link rel="alternate" href="https://proliferate.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13734"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Run a team of coding agents.

The open-source AI IDE for Claude Code, Codex, OpenCode, and more. Run agents in parallel, locally or in the cloud, and build reusable workflows.

- [Proliferate @ GitHub](https://github.com/proliferate-ai/proliferate).]]>
            </summary>
            <updated>2026-08-31T09:07:08+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13712</id>
            <title type="text"><![CDATA[Zeron]]></title>
            <link rel="alternate" href="https://github.com/zeronsh/comet" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13712"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Control your coding agents (Claude Code, Codex, Cursor, Grok, Hermes, Pi) locally by default, with optional multi-device sync.

Every device runs a small engine that stores sessions on that device. A new installation starts in local-only mode without an account or a network connection.]]>
            </summary>
            <updated>2026-08-21T14:00:25+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13699</id>
            <title type="text"><![CDATA[Silo]]></title>
            <link rel="alternate" href="https://getsilo.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13699"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[One window — every project, every agent.

Silo — for developers juggling coding agents across many projects. Every workspace alive at once, switch instantly. 100% open source, free forever.

- [Silo @ GitHub](https://github.com/silo-code/silo).]]>
            </summary>
            <updated>2026-08-20T15:23:46+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13691</id>
            <title type="text"><![CDATA[Munder Difflin]]></title>
            <link rel="alternate" href="https://munderdiffl.in/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13691"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Agent harness to run an office of your clones. local multi-agent harness.

Free, open source and performant — a multi-agent harness that works with the subscriptions you already pay for, on their hourly limits. It turns the terminal coding CLI you already run into a clone of you, one that keeps working while you&amp;#039;re away and coordinates a whole office of agents on your own machine.

Wraps Claude Code, Antigravity (Gemini), OpenAI Codex, xAI Grok, Kimi Code, Qwen, OpenCode, Crush, pi.dev, and GitHub Copilot CLI — with bring-your-own keys and local LLMs. Agents that message, route, and remember, coordinated by your clone (Michael) and visualized as avatars at work on a shared office floor.

- [Munder Difflin @ GitHub](https://github.com/chaitanyagiri/munder-difflin).]]>
            </summary>
            <updated>2026-08-20T11:37:12+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13619</id>
            <title type="text"><![CDATA[Paperclip]]></title>
            <link rel="alternate" href="https://paperclip.ing/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13619"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The app people use to manage AI agents for work.

Open-source orchestration for teams of AI agents.

If OpenClaw is an employee, Paperclip is the company.

Paperclip is a Node.js server and React UI that orchestrates a team of AI agents to run a business. Bring your own agents, assign goals, and track work and costs from one dashboard.

- [Paperclip @ GitHub](https://github.com/paperclipai/paperclip).]]>
            </summary>
            <updated>2026-08-12T12:17:26+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13603</id>
            <title type="text"><![CDATA[Ante]]></title>
            <link rel="alternate" href="https://github.com/AntigmaLabs/ante" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13603"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Ghost in your shell. Ante is a self-contained agent harness with a highly optimized core. It works like Claude Code or Codex, with none of their dependencies or model constraints. 

Ante is designed for cellular-native agents: like cells in an organism, tiny, expendable, massively replicated.]]>
            </summary>
            <updated>2026-08-11T11:52:16+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13468</id>
            <title type="text"><![CDATA[agent-manager]]></title>
            <link rel="alternate" href="https://github.com/YoanWai/agent-manager" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13468"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Terminal UI to manage AI coding-agent sessions (Claude Code, OpenCode, Codex, Grok Build) in tmux: live status, group tree, live pane preview, resource gauges.]]>
            </summary>
            <updated>2026-07-31T11:58:57+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13456</id>
            <title type="text"><![CDATA[Claude Code Merge Queue]]></title>
            <link rel="alternate" href="https://github.com/funador/claude-code-merge-queue" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13456"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The local merge queue for parallel Claude Code agents.

The local, zero-cost merge queue for parallel Claude Code agents. Several agents land, build, and test at the same time — this serializes it so push races, redundant heavy builds, and shared-resource test flakiness can&amp;#039;t happen.]]>
            </summary>
            <updated>2026-07-30T11:42:42+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13435</id>
            <title type="text"><![CDATA[Kritt]]></title>
            <link rel="alternate" href="https://kritt.ai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13435"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Orchestrate AI agents to find real vulnerabilities in code.

An open-source, self-hosted security research platform that turns focused AI analysis into de-duplicated, ranked findings with configurable validation and enrichment.

- [Kritt @ GitHub](https://github.com/Kritt-ai/open-kritt).]]>
            </summary>
            <updated>2026-07-27T12:30:44+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13419</id>
            <title type="text"><![CDATA[AgentSystem]]></title>
            <link rel="alternate" href="https://agentsystem.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13419"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Mission Control: Take Control of your Projects. Agents that Ship.

A focused desktop surface for launching, organizing, and repeating the agentic workflows that help you ship software faster.

- [AgentSystem @ GitHub](https://github.com/AgentSystemLabs/mission-control).

Related contents:

- [Why AWS Is Usually the Wrong Choice @ Web Dev Cody&amp;#039;s YouTube](https://www.youtube.com/watch?v=opbyn71T35I).]]>
            </summary>
            <updated>2026-07-27T05:41:56+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13272</id>
            <title type="text"><![CDATA[Background Agents]]></title>
            <link rel="alternate" href="https://backgroundagents.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13272"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Let Your Whole Team Ship Code. An open framework for background coding agents.

From code to tests to merged PR—automatically. Kick off a session at midnight, review the PR over breakfast.

- [Background Agents @ GitHub](https://github.com/ColeMurray/background-agents).]]>
            </summary>
            <updated>2026-07-15T06:03:41+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13227</id>
            <title type="text"><![CDATA[T3MP3ST]]></title>
            <link rel="alternate" href="https://github.com/elder-plinius/T3MP3ST" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13227"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[autonomous red teaming platform; multi-agent offensive-security meta-harness.

A multi-agent offensive-security framework, built to turn the AI coding agent you already run into a zero-day hunter.]]>
            </summary>
            <updated>2026-07-06T11:34:44+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13163</id>
            <title type="text"><![CDATA[Ablo]]></title>
            <link rel="alternate" href="https://www.abloatai.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13163"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The Collaboration Layer For AI Agents

One live, auditable state, shared by every agent working together.

When an agent and a person change the same thing at once, work gets lost: one edit silently clobbers another, or the agent acts on data that already moved. Ablo gives them one shared, typed write path so people, server actions, and agents can all work on the same rows without working blind.

- [Ablo @ GitHub](https://github.com/Abloatai/ablo).]]>
            </summary>
            <updated>2026-06-30T13:26:36+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13162</id>
            <title type="text"><![CDATA[Agent Swarm]]></title>
            <link rel="alternate" href="https://www.agent-swarm.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13162"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Multi-Agent Orchestration for AI Agents.
An AI agent swarm
that compounds daily.

Build an agent swarm for Claude Code and AI agents: a lead coordinates tasks, workers ship in their own containers, memory compounds with every run. Interact as you do with your remote colleagues.

- [Agent Swarm @ GitHub](https://github.com/desplega-ai/agent-swarm).]]>
            </summary>
            <updated>2026-06-30T13:26:06+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13160</id>
            <title type="text"><![CDATA[Craft Agents]]></title>
            <link rel="alternate" href="https://github.com/craft-ai-agents/craft-agents-oss" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13160"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Craft Agents is a tool we built so that we (at craft.do) can work effectively with agents. It enables intuitive multitasking, no-fluff connection to any API or Service, sharing sessions, and a more document (vs code) centric workflow - in a beautiful and fluid UI.

It uses the Claude Agent SDK and the Pi SDK side by side—building on what we found great and improving areas where we&amp;#039;ve desired improvements.]]>
            </summary>
            <updated>2026-06-30T11:46:38+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13153</id>
            <title type="text"><![CDATA[OpenFugu]]></title>
            <link rel="alternate" href="https://github.com/trotsky1997/OpenFugu" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13153"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Open reimplementation of Sakana Fugu — the &amp;#039;one model to command them all&amp;#039; LLM orchestrator. Read → run → train → serve. 

An open, runnable reverse-engineering of Sakana AI&amp;#039;s Fugu — the &amp;quot;one model to command them all&amp;quot; LLM orchestrator.

Fugu is sold as a single model; it is really a policy over models — a tiny coordinator that, per query, routes work to a pool of frontier LLMs and returns one answer. Sakana&amp;#039;s product and trained weights are closed. OpenFugu rebuilds the mechanism from the two papers + released artifacts, verifies it against real weights, trains a Conductor of our own, and serves it behind one OpenAI-compatible endpoint. Four stages, all working: read → run → train → serve.]]>
            </summary>
            <updated>2026-06-29T10:49:49+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13136</id>
            <title type="text"><![CDATA[good night, have fun (gnhf)]]></title>
            <link rel="alternate" href="https://github.com/kunchenguid/gnhf" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13136"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Before I go to bed, I tell my agents: good night, have fun.

gnhf is a ralph, autoresearch-style orchestrator that keeps your agents running while you sleep — each iteration makes one small, committed, documented change towards an objective. You wake up to a branch full of clean work and a log of everything that happened.

Related contents:

- [L8 Principal&amp;#039;s Agentic Engineering Workflow @ Kun Chen&amp;#039;s YouTube](https://www.youtube.com/watch?v=iQyg-KypKAA).]]>
            </summary>
            <updated>2026-06-29T05:44:38+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13134</id>
            <title type="text"><![CDATA[kunchenguid/firstmate:]]></title>
            <link rel="alternate" href="https://github.com/kunchenguid/firstmate" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13134"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Talk to one agent. Ship with a crew.

You can run one coding agent easily. But the moment you want three project tasks done in parallel - fixes, investigations, plans, audits - you become a tab-juggler: babysitting sessions, copy-pasting context between repos, forgetting which terminal had the failing test.

firstmate flips the model. You talk to a single agent - the first mate - and it runs the crew for you: spawning autonomous agents in tmux windows, giving each a clean git worktree, supervising them to completion, and handing you finished PRs, approved local merges, or standalone investigation reports. For larger fleets, you can opt in to persistent secondmates: domain supervisors that are still ordinary direct reports, but run from their own isolated firstmate homes. There is no app to install; the orchestrator is AGENTS.md, bundled skills, and helper scripts that any terminal coding agent can follow.

Related contents:

- [L8 Principal&amp;#039;s Agentic Engineering Workflow @ Kun Chen&amp;#039;s YouTube](https://www.youtube.com/watch?v=iQyg-KypKAA).]]>
            </summary>
            <updated>2026-06-29T05:41:06+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13094</id>
            <title type="text"><![CDATA[🔬 Scholar Loop]]></title>
            <link rel="alternate" href="https://github.com/renee-jia/scholar-loop" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13094"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Autonomous, multi-agent AI research — a PhD&amp;#039;s workflow on a single-GPU budget.

 An autonomous AI scientist: a multi-agent loop over literature, experiments, self-critique and write-up, with deterministic guards against reward-hacking and hallucination. 

ScholarLoop runs the loop a PhD actually runs: it reads the literature, forms a grounded hypothesis, runs real ML experiments, scores them against a frozen ground-truth metric, learns from its failures, and drafts a peer-reviewed write-up — autonomously, with a deterministic harness that keeps the agents honest and impossible to reward-hack.]]>
            </summary>
            <updated>2026-06-23T06:24:51+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12846</id>
            <title type="text"><![CDATA[Agent Executor (AX)]]></title>
            <link rel="alternate" href="https://github.com/google/ax" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12846"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Google&amp;#039;s open source distributed agent runtime.

AX, short for Agent eXecutor, is a distributed agent runtime. It provides a runtime that coordinates agentic loops, manages executions with event logging, and communicates with both local and remote actors. AX is designed for reliability, with native support for recovery and execution resumption, even in complex distributed setups.]]>
            </summary>
            <updated>2026-05-25T11:48:28+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12829</id>
            <title type="text"><![CDATA[Herdr]]></title>
            <link rel="alternate" href="https://herdr.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12829"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[One terminal. The whole herd.

Herdr is an agent runtime that runs inside your terminal. Keep your shell, SSH setup, fonts, and keybinds; add tmux-style persistence, mouse-native panes, blocked, working, and done agent state, and an API agents can drive. 

- [Herdr @ GitHub](https://github.com/ogulcancelik/herdr).

Related contents:

- [#87: Herding online exams @ Linux Matters](https://linuxmatters.sh/87/).
- [Herdr, un multiplexeur qui gère vos agents @ Grafikart :fr:](https://grafikart.fr/tutoriels/herdr-multiplexer-2351).]]>
            </summary>
            <updated>2026-08-14T12:15:01+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12713</id>
            <title type="text"><![CDATA[OpenWarp]]></title>
            <link rel="alternate" href="https://openwarp.zerx.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12713"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Bring any AI model into your terminal.

A fully decentralized fork of Warp. Six native AI protocols, third-party CLI agents as first-class Blocks, a built-in SSH + tmux host manager. Every credential, conversation and key stays on your machine.

- [OpenWarp @ GitHub](https://github.com/zerx-lab/warp).]]>
            </summary>
            <updated>2026-05-14T14:56:45+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/12692</id>
            <title type="text"><![CDATA[Ruflo]]></title>
            <link rel="alternate" href="https://github.com/ruvnet/ruflo" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12692"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Multi-agent AI orchestration for Claude Code.

Orchestrate 100+ specialized AI agents across machines, teams, and trust boundaries. Ruflo adds coordinated swarms, self-learning memory, federated comms, and enterprise security to Claude Code — so agents don&amp;#039;t just run, they collaborate.

 🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integration, and native Claude Code / Codex Integration]]>
            </summary>
            <updated>2026-05-14T09:21:24+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12626</id>
            <title type="text"><![CDATA[WUPHF]]></title>
            <link rel="alternate" href="https://wuphf.team/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12626"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Slack for AI employees with a shared brain. Get Claudes, Codexes and OpenClaws to collaborate and do your work autonomously while never losing context. 

 A collaborative office of AI employees that execute your playbooks, and get better at it everyday.

- [WUPHF @ GitHub](https://github.com/nex-crm/wuphf).]]>
            </summary>
            <updated>2026-04-27T11:54:33+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12518</id>
            <title type="text"><![CDATA[jc]]></title>
            <link rel="alternate" href="https://github.com/jeapostrophe/jc" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12518"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Claude Code orchestrator in one window.

 Orchestrate multiple Claude Code sessions across projects.
Review diffs, annotate code, send instructions — all from one window.

Related contents:

- [Don&amp;#039;t Wait for Claude @ Jay McCarthy](https://jeapostrophe.github.io/tech/jc-workflow/).]]>
            </summary>
            <updated>2026-04-12T15:54:10+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12506</id>
            <title type="text"><![CDATA[Multica]]></title>
            <link rel="alternate" href="https://multica.ai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12506"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[AI-Native Task Management.

Multica is an open-source platform that turns coding agents into real teammates. Assign tasks, track progress, compound skills — manage your human + agent workforce in one place.

- [Multica @ GitHub](https://github.com/multica-ai/multica).

Related contents:

- [Veille #51 — L&amp;#039;actu de la semaine @ Camille Roux :fr:](https://www.camilleroux.com/veille-51-lactu-de-la-semaine/).]]>
            </summary>
            <updated>2026-04-10T08:17:23+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12479</id>
            <title type="text"><![CDATA[OpenHarness]]></title>
            <link rel="alternate" href="https://github.com/HKUDS/OpenHarness" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12479"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Open Agent Harness.

OpenHarness delivers core lightweight agent infrastructure: tool-use, skills, memory, and multi-agent coordination.

Related contents:

- [Episode 661: Sink Your Claws In @ Linux Unplugged](https://linuxunplugged.com/661).]]>
            </summary>
            <updated>2026-04-09T06:16:00+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12477</id>
            <title type="text"><![CDATA[LobeHub :ch:]]></title>
            <link rel="alternate" href="https://lobehub.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12477"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Agent teammates that grow with you.

 The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction. 

- [LobeHub @ GitHub](https://github.com/lobehub/lobehub).

Related contents:

- [Episode 661: Sink Your Claws In @ Linux Unplugged](https://linuxunplugged.com/661).]]>
            </summary>
            <updated>2026-07-20T09:16:01+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12460</id>
            <title type="text"><![CDATA[Scion]]></title>
            <link rel="alternate" href="https://github.com/GoogleCloudPlatform/scion" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12460"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Run multiple agents in parallel — each in its own container, with its own workspace, collaborating on your code or project files simultaneously.

Scion is an experimental multi-agent orchestration testbed designed to manage &amp;quot;deep agents&amp;quot; running in containers.]]>
            </summary>
            <updated>2026-04-08T11:17:31+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12416</id>
            <title type="text"><![CDATA[Outworked]]></title>
            <link rel="alternate" href="https://github.com/outworked/outworked" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12416"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Cozy Office for Claude Code.

 Outworked is a desktop app that turns Claude into a team of AI employees.
Hire agents. Give them roles. Watch them write code, interact with the web, send messages,
and run scheduled tasks — all from an office on your Mac.]]>
            </summary>
            <updated>2026-04-03T17:26:17+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12312</id>
            <title type="text"><![CDATA[oh-my-claudecode]]></title>
            <link rel="alternate" href="https://yeachan-heo.github.io/oh-my-claudecode-website/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12312"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Teams-first Multi-agent orchestration for Claude Code. A weapon, not a tool.

Multi-AI orchestration plugin for Claude Code. Coordinate Claude, Gemini, and Codex with 19 specialized agents, 28 skills, and MCP-powered tools.

- [oh-my-claudecode @ GitHub](https://github.com/Yeachan-Heo/oh-my-claudecode).]]>
            </summary>
            <updated>2026-03-28T07:31:49+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12264</id>
            <title type="text"><![CDATA[Claude Octopus]]></title>
            <link rel="alternate" href="https://github.com/nyldn/claude-octopus" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12264"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Multi-LLM orchestration plugin for Claude Code — 8 providers (Codex, Gemini, Claude, Perplexity, OpenRouter, Copilot, Qwen, Ollama), 47 commands, 50 skills, Double Diamond workflows .

Multi-LLM orchestration plugin for Claude Code — coordinates Codex, Gemini, Perplexity, OpenRouter, Copilot, Qwen, and Ollama with consensus gates. Eight tentacles, zero blind spots.

Related contents:

- [Claude Octopus - Faites débattre 3 IA sur votre code @ Korben :fr:](https://korben.info/claude-octopus-orchestrateur-multi-ia-claude-code.html).]]>
            </summary>
            <updated>2026-03-23T16:27:30+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12192</id>
            <title type="text"><![CDATA[Air]]></title>
            <link rel="alternate" href="https://air.dev/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12192"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Run beloved agents side by side. Multitask with agents, stay in control.

JetBrains Air is the Agentic Development Environment where Codex, Claude Agent, Gemini CLI, and Junie execute independent task loops without interfering with each other.]]>
            </summary>
            <updated>2026-03-20T07:16:30+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/12175</id>
            <title type="text"><![CDATA[OpenViking]]></title>
            <link rel="alternate" href="https://openviking.ai/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12175"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The Context File System for AI Agents.
A Context DataBase for AI Agents.

Memory, Resource, Skill. Everything is a File.

- [OpenViking @ GitHub](https://github.com/volcengine/OpenViking).

Related contents:

- [10 GitHub Repositories for Modern Database Systems and Tools @ KD nuggets](https://www.kdnuggets.com/10-github-repositories-for-modern-database-systems-and-tools).]]>
            </summary>
            <updated>2026-06-03T05:53:42+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/12164</id>
            <title type="text"><![CDATA[Deep Agents]]></title>
            <link rel="alternate" href="https://docs.langchain.com/oss/python/deepagents/overview" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12164"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The batteries-included agent harness.

The easiest way to start building agents and applications powered by LLMs—with built-in capabilities for task planning, file systems for context management, subagent-spawning, and long-term memory. You can use deep agents for any task, including complex, multi-step tasks.

 Agent harness built with LangChain and LangGraph. Equipped with a planning tool, a filesystem backend, and the ability to spawn subagents - well-equipped to handle complex agentic tasks. 

Deep Agents is an agent harness. An opinionated, ready-to-run agent out of the box. Instead of wiring up prompts, tools, and context management yourself, you get a working agent immediately and customize what you need.

- [Deep Agents @ GitHub](https://github.com/langchain-ai/deepagents).

Related contents:

- [Your harness, your memory @ LangChain Blog](https://blog.langchain.com/your-harness-your-memory/).
- [Sandboxing an AI Agent @ Sajal Sharma](https://sajalsharma.com/posts/sandboxing-an-ai-agent/).]]>
            </summary>
            <updated>2026-07-02T12:11:08+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/12132</id>
            <title type="text"><![CDATA[Switchboard]]></title>
            <link rel="alternate" href="https://github.com/doctly/switchboard" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/12132"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A desktop app for browsing, searching, and managing CLI coding sessions. Your command center for Claude Code sessions.

Switchboard is a desktop app that gives you a unified view of all your Claude Code sessions across every project. Launch, resume, fork, and monitor sessions from a single window — no more juggling terminal tabs or digging through ~/.claude/projects to find that one conversation from last week.]]>
            </summary>
            <updated>2026-03-16T07:46:30+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/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/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/11838</id>
            <title type="text"><![CDATA[MimiClaw]]></title>
            <link rel="alternate" href="https://www.mimiclaw.io/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11838"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[: Run OpenClaw on a $5 chip. No OS(Linux). No Node.js. No Mac mini. No Raspberry Pi. No VPS.😗Local-first memory. Shareable. Portable. Privacy-first. Smarter than PicoClaw. 

MimiClaw turns a tiny ESP32-S3 board into a personal AI assistant. Plug it into USB power, connect to WiFi, and talk to it through Telegram — it handles any task you throw at it and evolves over time with local memory — all on a chip the size of a thumb.

- [MimiClaw @ GitHub](https://github.com/memovai/mimiclaw).]]>
            </summary>
            <updated>2026-02-17T06:47:25+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/11837</id>
            <title type="text"><![CDATA[ZeroClaw 🦀]]></title>
            <link rel="alternate" href="https://github.com/zeroclaw-labs/zeroclaw" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11837"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Fast, small, and fully autonomous AI assistant infrastructure — deploy anywhere, swap anything 🦀

 Zero overhead. Zero compromise. 100% Rust. 100% Agnostic.
⚡️ Runs on $10 hardware with &amp;lt;5MB RAM: That&amp;#039;s 99% less memory than OpenClaw and 98% cheaper than a Mac mini!]]>
            </summary>
            <updated>2026-02-17T06:46:25+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/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/11664</id>
            <title type="text"><![CDATA[multiclaude]]></title>
            <link rel="alternate" href="https://github.com/dlorenc/multiclaude" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/11664"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Why tell Claude what to do when you can tell Claude to tell Claude what to do?

Multiple Claude Code agents. One repo. Controlled chaos.

multiclaude spawns autonomous Claude Code instances that coordinate, compete, and collaborate on your codebase. Each agent gets its own tmux window and git worktree. You watch. They work. PRs appear.]]>
            </summary>
            <updated>2026-02-02T06:32:27+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/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/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/3241</id>
            <title type="text"><![CDATA[KaibanJS]]></title>
            <link rel="alternate" href="https://www.kaibanjs.com/" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/3241"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[The JavaScript Framework for Building Multi-Agent Systems.

KaibanJS is a JavaScript-native framework for building and managing multi-agent systems with a Kanban-inspired approach. 

- [KaibanJS @ GitHub](https://github.com/kaiban-ai/KaibanJS).]]>
            </summary>
            <updated>2025-08-29T00:56:55+00:00</updated>
        </entry>
    </feed>
