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

2,905–2,928 of 4,275
milind-soni

tiptour-macos

★ 670

Open-Source alternative to Google's AI-enabled pointer.

Swift
★ 670

A LLM-based Agent that predict its tasks proactively.

Python
Varnan-Tech

opendirectory

★ 670

AI Agent Skills built for Founders who hate Marketing

Python
AgentTeam-TaichuAI

ScienceClaw

★ 669

ScienceClaw is a personal research assistant built with LangChain DeepAgents and AIO Sandbox infrastructure, adopting a completely new architecture beyond OpenClaw. It offers stronger security, better transparency, and a more user-friendly experience.

Python
★ 667

NORDEF Matrix Open Control: model-independent AI safety belt with 0/1/2 decisions, Ed25519 root gate, replay protection, evidence chain, and incident-pattern eval bank

Python
nv-tlabs

Gamma-World

★ 667

Implementation of Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players

Python
scanaislop

aislop

★ 667

Catch and fix the code-quality issues AI coding agents leave behind - dead code, unsafe casts, swallowed errors, duplication, security risks, and more. 50+ deterministic rules across 10 language targets, with CLI, CI, and GitHub Actions. No LLM at runtime. MIT.

TypeScript
Tencent-Hunyuan

Hy3

★ 667

Hy3 (295B A21B), a leading reasoning and agent model in its size, with great cost efficiency.

Python
★ 666

A Model Context Protocol (MCP) that allows Claude Desktop and other AI tools (Claude Code, Cursor, Antigravity, etc.) to read, analyze, and modify Figma designs

TypeScript
★ 666

Local-first open-source multi-profile fingerprint browser based on Chromium and Electron

TypeScript
★ 666

DeepSeek Harness 零代码桌面端｜一键启动，支持 Windows 与 macOS；内置插件发现、热点插件推送、一键安装与管理、AI 智能推荐和视觉增强。

TypeScript
henrydaum

second-brain

★ 666

Second Brain is an agentic framework that acts as an operating system, using local file intelligence, workflow automation, and LLMs to complete tasks and communicate over multiple modalities and messaging platforms.

Python
ThibautBaissac

rails_ai_agents

★ 665

Specialized AI skills, agents, rules and hooks for modern Rails AI driven-development + Spec-Driven-Development kit + MCP

Shell
Snailclimb

AIGuide

★ 664

AI 应用开发、AI 编程实战与面试指南，涵盖 LLM、Agent、RAG、MCP、Claude Code、Codex 等核心技术与工程实践。

coleam00

skills

★ 663

The agent skills I actually use to build software with coding agents. The PIV loop, planning, worktrees, and the meta-skills for building your own AI Layer.

Python
corespeed-io

wechatbot

★ 663

微信 iLink Bot SDK for OpenClaw/AI Agent

TypeScript
wangxijie001

yoji

★ 663

有情绪的 AI 桌面伴侣 | 隐私优先 · 语音唤醒 · 协助办公 · MCP 无限扩展 | An AI desktop companion with emotions — privacy-first, voice wake, office assistance, and MCP extensibility

TypeScript
★ 662

OpenAI Codex: The Complete Guide · 橙皮书系列 · GPT-5.5 时代的 AI 编程实战手册

HTML
MatrixAges

polywise

★ 662

The open source agentic content system to make your contents alive. Self-hosted on any platform. ◑

TypeScript
★ 662

🔧 The open guide to Harness Engineering — concepts, tutorials, papers, tools, and resources for building and managing AI agent runtimes.

TypeScript
★ 662

基于dsh web实现的多种模式，目的是服务于redteam进行授权的安全研究，覆盖渗透测试、红队评估、代码审计等范围领域，请勿用于非法行为。（允许二开，赋予模块各位自己的业务逻辑，方法论只有自己熟练的才好用，好的方法论=好的生态）

Python
★ 662

A.S.E (AICGSecEval) is a repository-level AI-generated code security evaluation benchmark developed by Tencent Wukong Code Security Team.

Python
viettranx

3dviz-pro-max

★ 662

Agent skill for creative 3D visualization: turn an idea into a Three.js/Blender scene worth exploring. Claude Code + Codex plugin, 223 recipes, 440 knowledge records, 22 proved kits, 37 runnable studies.

JavaScript
ccch1mneyyy

working-activity

★ 661

Lively Working-line extension for pi CLI and DSH

TypeScript