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

1,609–1,632 of 3,152

Agent-Field

SWE-AF

★ 1,002

Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, and ship.

larashero3-dotcom

lieflat-gongwen

★ 1,002

通过102万字语料提炼的公文写作 skill，把公文写作风格变成可测量、可验收的量化数据

Python

tensorlakeai

tensorlake

★ 998

Tensorlake is a serverless runtime for sandboxes and deploying background agentic applications

Python

Human-Agent-Society

CORAL

★ 993

Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi-agent evolution. Accepted at COLM 2026.

Python

charmbracelet

fantasy

★ 992

Build AI agents with Go. Multiple providers, multiple models, one API. 🧙

jiweiyeah

Skills-Manager

★ 992

Free, open-source desktop manager for AI Agent Skills. Write a skill once, sync it to 32 AI coding tools (Claude Code, Codex, Cursor, Gemini CLI, and more) via symlinks. Local-first, MIT licensed. macOS, Windows, Linux.

TypeScript

callstackincubator

cali

★ 991

AI agent for building React Native apps

TypeScript

MadAppGang

claudish

★ 991

Claude Code. Any Model. The most powerful AI coding agent now speaks every language.

TypeScript

shanraisshan

codex-cli-best-practice

★ 990

from vibe coding to agentic engineering - practice makes codex perfect

Python

Deuz-AI

Deuz-SDK

★ 988

Zero-dependency TypeScript framework for production AI agents: durable execution, long-term memory, hybrid RAG, MCP tool calling, human-in-the-loop approval, planning and CodeAct sandboxes. One streaming API for Claude, GPT, Gemini, Grok, Mistral and DeepSeek — Node, Bun, Deno, serverless and edge.

TypeScript

Azure-Samples

AI-Gateway

★ 987

Labs to explore AI Models, MCP servers, and Agents with the AI Gateway powered by Azure API Management and Microsoft Foundry 🚀

Jupyter Notebook

agent-sh

agentsys

★ 986

AI writes code. This automates everything else · 24 plugins · 49 agents · 44 skills · for Claude Code, OpenCode, Codex, Cursor, Kiro.

JavaScript

Pantheon-Security

medusa

★ 986

AI-first security scanner. NEW in v2026.7: Claude Code compromise detection — vet .claude/ hooks, permissions & skills before you clone — plus an always-on AI attack-signature scanner and native Rust & PHP rules. Also: medusa scan --git to vet any repo, medusa secrets scan for leaked API keys. 40,000+ patterns, zero setup.

Python

zhu1090093659

spec_driven_develop

★ 979

Spec-driven development workflow for AI coding agents: architecture-first planning, task decomposition, GitHub Issue/PR tracking, Deep Discuss, and adaptive control for Claude Code, Codex, Cursor, and other Markdown-capable agents.

Shell

principia-ai

WriteHERE

★ 977

An Open-Source AI Writing Project.

Python

TryCaspian

caspian-sdk

★ 977

Agent communication SDK. The open-source agent communication layer for AI agents — email, WhatsApp, Slack, Discord, Telegram, SMS. Python & TypeScript.

Python

jjang-ai

mlxstudio

★ 975

MLX Studio - Easiest way to run LLM's on your Mac. All in one engine.

lancedb

vectordb-recipes

★ 974

Resource, examples & tutorials for multimodal AI, RAG and agents using vector search and LLMs

Jupyter Notebook

derisk-ai

OpenDerisk

★ 973

AI-Native Risk Intelligence Systems, OpenDeRisk——Your application system risk intelligent manager provides 7* 24-hour comprehensive and in-depth protection.

Python