ai-agent
The framework for building agents
Like Next.js for agents. Build durable agents with one folder. eve is a filesystem-first framework for durable AI agents. Core agent capabilities live in conventional locations, so projects are easier to inspect, extend, and operate.
Related contents:
The Destructive Command Guard (dcg) is for blocking dangerous git and shell commands from being executed by agents.
A high-performance hook for AI coding agents that blocks destructive commands before they execute, protecting your work from accidental deletion across Claude Code, Codex CLI, Gemini CLI, Copilot CLI, VS Code Copilot Chat, Cursor, Hermes Agent, Grok (xAI), and related tools.
The open agent runtime.
Open, self-hostable agentic runtime for organizations — durable, replayable agent sessions, human approvals, governed credentials and memory, running in managed sandboxes or on your own hardware. Apache-2.0.
top-style TUI for monitoring AI coding agent sessions.
Your window into what your AI coding agents are doing, sitting in the terminal, where you run them. agtop is a top-style terminal dashboard that tracks every Claude Code and Codex session on your machine: spend, token usage, context pressure, CPU load, tool invocations, and more. All in one place, live.
push frontier AI to it limits. A fork of the Codex CLI with validation, automation, browser integration, multi-agents, theming, and much more. Orchestrate agents from OpenAI, Claude, Gemini or any provider.
Every Code (Code for short) is a fast, local coding agent for your terminal. It's a community-driven fork of openai/codex focused on real developer ergonomics: Browser integration, multi-agents, theming, and reasoning control — all while staying compatible with upstream.
An iMessage-based personal agent you can run with either your Claude Code subscription or your Codex / ChatGPT subscription.
iMessage personal agent: choose Claude Agent SDK (Claude Code) or Codex app-server runtime (Codex/ChatGPT), with memory, sub-agents, automations, integrations.
A coding agent for any model
Works with frontier models, but also strives to be as reliable as possible with smaller models, including local ones. Designed for tight context windows and limited resources. Free, open-source, and easy to set up.
Related contents:
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.
Simple, Fast, Vibe‑Ready ! Official Harness for GLM-5.2.
ZCode combines the best AI agents with your existing tools so you can plan, code, review, and deploy without friction.
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've desired improvements.
Godcoder doesn't just use a harness. It writes one, improves it, and optimizes it — autonomously, in real time.
A local-first, open-source coding agent for your desktop. Bring your own LLM key; your code stays on your machine and only ever leaves to the model provider. The AI Agent builds its own Harness.
Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation.
Related contents:
The VanillaJS Agent UI Library. Create agentic front-end experiences for the web in VanillaJS™️. Lightweight, extensible, and WebMCP-native.
Persona helps you create agentic front-end experiences for the web, in pure JS. Lightweight, extensible, and WebMCP-native.
peerd is an extension that turns your existing browser into an agent workstation.
The first AI agent harness native to the browser. A Chrome/Firefox extension that runs the agent loop in your browser — drives your tabs, spins up sandboxed compute (JS notebooks, WASM Linux VMs, client-side apps), and shares what it builds peer-to-peer. BYOK · no backend · no telemetry.
Three primitives. Zero integration cost.
Effortlessly compose, extend, and observe every service in real-time for the first time ever. iii is the easiest way to compose, extend, and observe every service in your stack in real time.
Every backend starts as a project before the first line of business logic. Queues, cron, HTTP, state, observability, agents, and sandboxes each usually bring their own integration story. iii collapses that into one live system surface.
Framework for Agent-Native Apps. Agentic Applications You Own.
Start with a chat-first app and the app-agent loop. Add actions, screens, jobs, and workflows as your agent grows.
A next-generation AI coding assistant for developers. Unlimited context lets you understand, build, and collaborate more efficiently.
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.
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.
Run Claude Code, Codex, Copilot, OpenCode from anywhere.
Run any coding agent from your phone, desktop, or terminal. Self-hosted, multi-provider, open source.
Orchestrate sandboxed coding agents in TypeScript with sandcastle.run().
A TypeScript library for orchestrating AI coding agents in isolated sandboxes.
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's open source and powered by GitHub Actions.
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.
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.
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
Run Coding Agents in Sandboxes. Control Them Over HTTP. Supports Claude Code, Codex, OpenCode, and Amp.
Related contents:
Persistent & Secure sandboxes for AI agents.
Give your agents lightning-fast sandboxes with persistent state and versioned filesystems.
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:
Free AI Router. Smart Fallback for Claude, Codex & 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.
Go full --yolo. We'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
Related contents:
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.
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
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.
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.
Save 98% of your AI coding agent's context window.
Context window optimization for AI coding agents. Sandboxes tool output, 98% reduction. 15 platforms
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.
Related contents:
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.
A toolkit for spec-driven software development. Stop writing prompts, start writing specs. Ship better quality software and minimize slop.
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.
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.
🤗 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.
The Agentic Development Environment.
Warp is an agentic development environment, born out of the terminal. Use Warp's built-in coding agent, or bring your own CLI agent (Claude Code, Codex, Gemini CLI, and others).
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.
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:
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).
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.
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.
Close the loop with Argent Agentic AI Toolkit for React Native & 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.
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't reach.
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:
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:
A 30-minute talk sharing practical lessons from building real production projects with AI coding agents — from brainstorming to shipped code.
Related contents:
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.
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.
Related contents:
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.
tmux config with built-in terminal automation and agent-to-agent communication.
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.
Your AI agent configs, skills, and instructions on every device. One config repo. Every agent. Every machine.
You'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.
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:
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'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.