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

1,825–1,848 of 3,152

KylinMountain

TradingAgents-AShare

★ 832

A 股多智能体智能投研系统 — 基于 TradingAgents 架构，15 名 AI Agent 模拟机构协作与实时辩论对抗，全流程可视化，支持 OpenClaw / Claude Code 集成，Docker 一键部署。

Python

AgentWorkforce

relay

★ 831

Real time communication for agents. Wake on message, channels, DMs and actions. Useful for orchestrating agents.

TypeScript

es617

claude-replay

★ 831

Convert AI coding agent sessions (Claude Code, Cursor, Codex, Gemini, OpenCode, Kimi Code, Hermes) into self-contained, embeddable HTML replays

JavaScript

huangjia2019

rag-in-action

★ 831

End-to-end RAG system design, evaluation, and optimization. 极客时间RAG训练营，RAG 10大组件全面拆解，4个实操项目吃透 RAG 全流程。RAG的落地，往往是面向业务做RAG，而不是反过来面向RAG做业务。这就是为什么我们需要针对不同场景、不同问题做针对性的调整、优化和定制化。魔鬼全在细节中，我们深入进去探究。

Jupyter Notebook

usehelix

helix

★ 831

Self-healing infrastructure for AI agent payments. 90.3% auto-recovery.

TypeScript

ZeroZ-lab

cc-design

★ 831

High-fidelity HTML design and prototype guidance skill for AI agents

JavaScript

BradGroux

veritas-kanban

★ 830

Lightweight orchestration harness built for your AI agents. The unfiltered truth about where your project stands.

TypeScript

context-machine-lab

sleepless-agent

★ 830

🤖 24/7 AI agent that maximizes Claude Code Pro usage via Slack. Auto-processes tasks, manages isolated workspaces, creates Git commits/PRs, and optimizes day/night usage thresholds.

Python

Ayanami0730

deep_research_bench

★ 829

DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents

Python

MartinDelophy

ai-video-editor

★ 827

Open-source, local-first video editor where creators and AI agents edit the same real timeline.

JavaScript

AgnosticUI

agnosticui

★ 826

AgnosticUI Local (v2) is a CLI-based UI component library that copies components directly into your project. Works with AI tools, agent-driven UIs, and prompt-ready workflows.

TypeScript

formulahendry

wechat-acp

★ 826

Bridge WeChat chat messages to any ACP-compatible AI agent (Claude, Codex, Copilot, Qwen, Gemini, OpenCode, OpenClaw, Hermes, Kiro, Kimi, Pi and more)

TypeScript

heurist-network

heurist-agent-framework

★ 825

A flexible multi-interface AI agent framework for building agents with reasoning, tool use, memory, deep research, blockchain interaction, MCP, and agents-as-a-service.

Python

Wh0am123

MCP-Kali-Server

★ 825

MCP configuration to connect AI agent to a Linux machine.

Python

yz671

viewllm

★ 825

Single-binary HTML report viewer for LLM-generated artifacts

HTML

metauto-ai

agent-as-a-judge

★ 824

👩‍⚖️ Agent-as-a-Judge: The Magic for Open-Endedness

HTML

riponcm

projectmem

★ 824

Open-source coding agents memory. Records issues, attempts, fixes and decisions, then warns your agent before it repeats an approach that already failed. Native MCP server for Claude Code, Cursor, Antigravity and Codex. 100% local, no cloud, no telemetry. MIT.

Python

jonigl

mcp-client-for-ollama

★ 823

Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved preferences.

Python

riba2534

happyclaw

★ 823

自托管、多用户、智能体优先的 Agent 工作台

TypeScript

suyoumo

ClawProBench

★ 823

ClawProBench is a live-first benchmark harness for evaluating LLM agents in the OpenClaw runtime with deterministic grading and repeated-trial reliability.

Rust

xixihhhh

clipforge

★ 823

ClipForge（原『带货剪手』/ daihuo-jianshou）：开源 AI 带货短视频神器——上传一张商品图，AI 自动提炼卖点 + 写种草脚本 + 锁定商品原图不变形 + 配画面/配音/字幕，一键产出抖音小店 / 快手 / 小红书 / TikTok Shop 卖货短视频。0 成本批量出片、开源无水印、本地自部署。也支持一句话主题成片。Open-source AI e-commerce/UGC short-video generator.

TypeScript