AI channel
AI agents

Open-source AI agents

An AI agent is a program that uses a language model to decide what to do next, calls tools such as a browser, a code interpreter or an API, and repeats until the task is done. The projects here range from frameworks for building your own agents to finished agents that write code, browse the web or run business workflows.

How to choose

Compare three things. Which models it can use: a single provider, or any OpenAI-compatible endpoint including local ones. How it limits what the agent may do: sandboxing, approval steps and permission lists. And whether it keeps memory between steps and sessions. An agent that runs code or shell commands should run in a sandbox, so check that before giving it access to your machine.

Most-starred projects

2,353–2,376 of 4,275
★ 962

Research archive of Claude Code source and runtime artifacts reconstructed from published npm source maps.

TypeScript
cdxiaodong

cain-agent

★ 961

Real-world AI penetration testing engineer for authorized assessments — built-in cloud module covering AWS/Azure/GCP + Aliyun/Tencent/Huawei clouds. Built on Claude Agent SDK

Python
s-kostyaev

ellama

★ 961

Work with local and cloud LLMs from Emacs.

Emacs Lisp
Bennettxai

FounderOS-DEMO

★ 960

An open-source, single-operator business command center: run a one-person operated company as AI-assisted departments (comms, funnel, social, finances, agents, and a knowledge graph) from one live dashboard.

TypeScript
block

berd

★ 960

a desktop app for getting work done with any model

TypeScript
CopilotKit

aimock

★ 959

Mock everything your AI app talks to — LLM APIs, MCP, A2A, AG-UI, vector DBs, search. One package, one port, zero dependencies.

TypeScript
LearnPrompt

luban-skill

★ 959

鲁班 | Luban — 把'能用的Skill'打磨成'能被装、能传播、能验证、能进化'的公共资产。Agent skill-polishing workshop: 验料·访行·过尺·慢刨·回炉

Shell
Rath-Team

OpenRath

★ 959

An open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows.

Python
csyqlz

VOZEB-PRO

★ 958

VOZEB PRO:从创作简报、视觉方向、物料规划到一致性生成与自动视觉复盘的 AI 创作工作台。

TypeScript
Rheosoph

flow-like

★ 957

Flow-Like: Strongly Typed Enterprise Scale Workflows. Built for scalability, speed, seamless AI integration and rich customization.

Rust
agentic-community

mcp-gateway-registry

★ 956

Enterprise-ready MCP Gateway & Registry that centralizes AI development tools with secure OAuth authentication, dynamic tool discovery, and unified access for both autonomous AI agents and AI coding assistants. Transform scattered MCP server chaos into governed, auditable tool access with Keycloak/Entra integration.

Python
lynaghk

vibe

★ 956

Easy Linux virtual machine on MacOS to sandbox LLM agents.

Rust
microsoft

wassette

★ 956

Wassette: A security-oriented runtime that runs WebAssembly Components via MCP

Rust
AgileRL

AgileRL

★ 955

Streamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools, with 10x faster training through evolutionary hyperparameter optimization.

Python
MeisnerDan

mission-control

★ 954

Open-source task management for the agentic era. The command center for solo entrepreneurs who delegate work to AI agents.

TypeScript
google

sam

★ 952

SAM Sovereign Agent Mesh

Go
★ 951

🚀 Run Codex Mobile Anywhere: Linux, Windows, or Termux on Android 🚀

TypeScript
Mininglamp-OSS

octo-ios

★ 950

OCTO iOS Client — Open-source enterprise IM

Objective-C
russelleNVy

three-man-team

★ 950

A structured 3-agent AI dev team — Architect, Builder, Reviewer. Built from production use. Token-optimized. Works with Claude Code, VS Code, Cursor, and any AI that supports context files.

Shell
suboss87

FDEOps

★ 950

Forward deployed engineering skills for AI coding agents.

JavaScript
weaviate

recipes

★ 950

This repository shares end-to-end notebooks on how to use various Weaviate features and integrations!

Jupyter Notebook
luongnv89

asm

★ 949

The universal skill manager for AI coding agents.

TypeScript
RizRiyz

luvus

★ 948

Mission control for your AI agents

Rust