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

3,529–3,552 of 4,299
★ 484

Practical system design, tools, and hands-on resources for building Gen-AI agents & agentic AI systems.

Python
baby-llm

baby-agent

★ 484

AI agent tutorials for backend developers without AI background. 适合后端工程师的零基础 AI Agent 教程

Go
exon-research

genomi

★ 484

Local-first, open-source Claude Science alternative, before Claude Science is a thing. Turn your AI agent into personal DNA expert.

Python
Jia-Ethan

grok-keysmith

★ 484

Preview-first Grok Build instruction deployment with compat and hook isolation, durable recovery, and layered uninstall.

Python
Solsynth

MaidKit

★ 484

The ultimate SSH toolkit for developers

Dart
★ 484

一个纯前端的极简Markdown编辑器，单HTML文件，打开即用，完全免费。A minimalist browser-based Markdown editor in a single HTML file. Live preview, auto-save, distraction-free writing.

HTML
★ 483

A robust enterprise application sample (deployed on ACA) that leverages MCP and multiple AI agents orchestrated by Langchain.js, Llamaindex.TS and Microsoft Agent Framework.

TypeScript
Justin0504

Aegis

★ 483

Runtime policy enforcement for AI agents. Cryptographic audit trail, human-in-the-loop approvals, kill switch. Zero code changes.

TypeScript
★ 483

🏯 Claude Code / Codex skill — transform Chinese architecture, cultural places & travel photos into art-directed editorial posters with GPT Image. 中国古建筑与在地文化照片 → 艺术指导海报

Python
radareorg

r2ai

★ 483

LLM-based reversing for radare2

C
shadcn-labs

agentcn

★ 483

shadcn/ui, but for building agents. 🤖

TypeScript
TokenRollAI

llmdoc

★ 483

TokenRoll LLMDoc for Coding Agent

TypeScript
ZingerLittleBee

Heeler

★ 483

Native iOS agent console for herdr — watch and drive the coding agents on your machines over SSH, with a real libghostty terminal, QR pairing, and push notifications when an agent needs you

Swift
★ 482

MCP Playbooks for AI agents

TypeScript
jackson-video-resources

markov-hedge-fund-method

★ 482

Markov regime detection skill + one-shot install prompt + Pine indicator. Companion to Quant Series video 1. Framework by Roan (@RohOnChain).

Python
runagent-dev

runagent

★ 482

RunAgent simplifies serverless deployment of your AI agents. With a powerful CLI, multi-language SDK support, built-in agent invocation & streaming suppprt.

Python
taylorsatula

mira-OSS

★ 482

This is the public release of MIRA OS. Discrete memories decay through momentum loss, tools auto-configure when dropped into tools/ folder, and the system prompt composes from modular trinkets. I would like to think I've made an elegant brain-in-box. You load it and send cURL requests - it talks back, learns, and uses tools. Contributions welcome.

Python
★ 482

Paper-Agent 是一个面向科研人员和学生的智能论文检索与调研工具。项目基于多智能体协作架构（LangGraph），通过自然语言处理（NLP）、自动化搜索，帮助用户高效查找学术论文、分析文献内容，并进行论文调研。Paper-Agent 支持多平台集成、关键词搜索、自动分析、论文调研，提升了学术研究的效率。适用于论文写作、学术调研、科研项目管理等多种场景，是学术调研的理想助手。

Python
AgentFlocks

flocks

★ 480

Flocks is an agentic SecOps platform.

Python
Miasyster

QuantGPT

★ 480

Agent-driven alpha factory — LLM autonomously designs, backtests, and submits factors to WorldQuant BRAIN

Python
phoenix-zhou

multi-agent

★ 480

A multi-agent travel assistant system built using the **Agent2Agent (A2A)** protocol and **MCP (Model Context Protocol)**

Python
SAIL-Research-Lab

agentic-web

★ 480

Agentic Web: Weaving the Next Web with AI Agents.

baidu-baige

LoongFlow

★ 479

LoongFlow is an expert-grade Agent framework for Loop Engineering. Through a Plan-Execute-Summary loop and structured experiential memory, it enables AI to continuously think, execute, reflect, and evolve across complex software engineering, mathematical, and machine learning tasks.

Python
elevenlabs

skills

★ 479

Collections of skills for building with ElevenLabs

Python