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

2,041–2,064 of 4,275
moltlaunch

cashclaw

★ 1,222

An autonomous agent that takes work, does work, gets paid, and gets better at it.

TypeScript
xianyu110

gpt-codex

★ 1,221

这是一个关于 OpenAI CodeX 的完整教程网站，专为国内开发者打造。

HTML
jieyefriic

rp-engine

★ 1,218

YAML-native agent workflow execution engine, written in Rust

Rust
NVIDIA-NeMo

Gym

★ 1,217

Evaluate and improve models and agents using environments

Python
★ 1,214

为纯文本模型"看图“设计更好的视觉工具箱和技能，支持多图理解，图片问答，前端UI还原、GUI 自动化等，并可选无缝接入多个主流agent，直接识别粘贴图片｜ A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode

Python
langchain-ai

openevals

★ 1,214

Readymade evaluators for your LLM apps

Python
Spark-To-Paper-Skills

paperjury

★ 1,214

Pre-submission AI review stress-test for research papers. A Claude Code skill: review, verdict, revise, verify.

JavaScript
cinderline

northcinder

★ 1,213

Open-source MCP server for comparing products and asking the buyer before purchase.

JavaScript
★ 1,210

A multi-llm Emacs shell (ChatGPT, Claude, DeepSeek, Gemini, Kagi, Ollama, Perplexity) + editing integrations

Emacs Lisp
ZHangZHengEric

Sage

★ 1,210

Multi-Agent System Framework For Complex Tasks

Python
i365dev

free4chat

★ 1,205

Free4Chat provides the temporary boundary. Participants bring the capabilities.

TypeScript
laude-institute

headlong

★ 1,205

An open source agent microharness featuring persistent agency and recursive LLMs. Of bash, by bash, for bash; it's shells all the way down.

Shell
brainlid

langchain

★ 1,204

Elixir implementation of a LangChain style framework that lets Elixir projects integrate with and leverage LLMs.

Elixir
clacky-ai

openclacky

★ 1,203

The most Token-efficient open-source AI Agent

Ruby
heyhuynhgiabuu

proxypal

★ 1,202

A desktop app that lets you use your AI subscriptions (Claude, ChatGPT, Gemini, GitHub Copilot) with any coding tool. Wraps CLIProxyAPI with a clean UI for managing connections and tracking usage.

TypeScript
iDC-NEU

YiGraph

★ 1,202

YiGraph is an LLM-driven agent for autonomous Graph Data Analytics based on Analytics-Augmented Generation. 易图（YiGraph）是一套基于 AAG（分析增强生成）框架构建的图分析智能体系统，致力于挖掘数据之间的关联关系，释放数据价值。

Python
★ 1,201

Agentic SOC Platform: A powerful, flexible, open-source, and agent-centric automated security operations platform (AI SOC)

Python
letta-ai

agent-file

★ 1,201

Agent File (.af): An open file format for serializing stateful AI agents with persistent memory and behavior. Share, checkpoint, and version control agents across compatible frameworks.

TypeScript
CreminiAI

skillpack

★ 1,200

Pack and deploy local AI agents for your team in minutes

TypeScript