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

2,881–2,904 of 4,275

GeminiLight

MindOS

★ 678

MindOS is a Human-AI Collaborative Mind System, where human thinks and agents act. Globally sync your mind for all agents: transparent, controllable, and evolving symbiotically.

TypeScript

JuliusBrussee

cavemem

★ 678

Frozen — cross-agent persistent memory for coding assistants. Still works; the compressed-memory core now ships inside JuliusBrussee/caveman.

TypeScript

MagicCube

helixent

★ 678

Helixent is a small library for building ReAct-style AI agent loops based on the Bun stack.

TypeScript

talesofai

comfyui-browser

★ 678

An image/video/workflow browser and manager for ComfyUI.

Svelte

rusiaaman

wcgw

★ 677

Shell and coding agent on mcp clients

Python

witchan

ios-mcp

★ 677

iOS MCP: MCP management tool for jailbroken iPhones, enabling developers and AI agents to inspect and control devices.

Objective-C

BorisPolonsky

dify-helm

★ 676

Deploy langgenious/dify, an LLM based app on kubernetes with helm chart.

Go Template

harbor-framework

terminal-bench-science

★ 676

Terminal-Bench-Science: Evaluating AI agents on research workflows across scientific domains

Python

SiriusFzh

NovaForge

★ 676

锻造你的知识体系 | 考研·考公·专业课·科研·项目·竞赛通用笔记模板。LaTeX+Typst+Markdown三版本，7步模块化结构，6种场景模板，一键换色，开箱即用。

TeX

framerslab

agentos

★ 675

TypeScript AI agent framework: cognitive memory, runtime tool forging, multi-agent orchestration, 11 LLM providers.

TypeScript

jmerelnyc

Photo-agents

★ 675

Autonomous self-evolving agents. Vision-grounded layered memory and self-written skills for LLM agents that operate your computer.

Python

sou350121

VLA-Handbook

★ 675

本项目旨在为致力于进入VLA(Vision-Language-Action)领域的算法工程师提供一份全中文、实战导向的学习/面试手册。不同于通用的 CV/NLP 面试指南，本项目聚焦于 Robotics 特有的挑战

HTML

automateyournetwork

netclaw

★ 674

An AI agent that claws through your network

Python

Ar9av

PaperOrchestra

★ 673

An automated AI research-paper writer based off Google's PaperOrchestra paper's implementation through a skills - benchmark + autoraters using any coding agent (Claude Code, Cursor, Antigravity, Cline, Aider). No API keys, no LLM SDKs.

Python

claude-code-chinese

claude-code-guide

★ 673

Claude Code国内如何使用？最容易懂的 Claude Code 介绍与教学指南（2026年最新）

fayazara

macos-app-skills

★ 673

AI coding agent skills for building, shipping, and maintaining native macOS apps

Swift

h5i-dev

h5i

★ 673

Fast, security-first headless browser for AI agents. Built for automation, red teaming, web testing, and scraping, with direct HTTP traffic control and auditable sessions. Pure Rust, no Chromium or V8.

Rust

hamzafer

cursor-commands

★ 673

Cursor Custom Slash Commands

typedef-ai

fenic

★ 673

Semantic DataFrames for humans and agents

Python

Bessouat40

RAGLight

★ 672

RAGLight is a modular framework for Retrieval-Augmented Generation (RAG). It makes it easy to plug in different LLMs, embeddings, and vector stores, and now includes seamless MCP integration to connect external tools and data sources.

Python