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

1,057–1,080 of 4,276

TurixAI

TuriX-CUA

★ 3,171

This is the official website for TuriX Computer-use-Agent

Python

xlang-ai

OSWorld

★ 3,168

[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

Python

yilewang

llm-for-zotero

★ 3,168

An open-source research agent system for your Zotero library.

TypeScript

cosmicstack-labs

mercury-agent

★ 3,167

Soul-driven AI agent with permission-hardened tools, token budgets, and multi-channel access. Runs 24/7 from CLI or Telegram.

TypeScript

google-deepmind

science-skills

★ 3,167

GDM Science Skills to speed up agentic scientific workflows with better grounding and higher token efficiency. Integrate insights from AlphaGenome, AFDB, UniProt and 30+ other databases and tools.

Python

mikeyobrien

ralph-orchestrator

★ 3,164

An improved implementation of the Ralph Wiggum technique for autonomous AI agent orchestration

Rust

lackeyjb

playwright-skill

★ 3,162

General-purpose Playwright automation for coding agents

JavaScript

Forward-Future

loopy

★ 3,161

A library of practical AI-agent loops and an installable skill for finding, adapting, and designing repeatable agent workflows.

JavaScript

wquguru

harness-books

★ 3,159

📚 Two books on harness engineering — the design philosophies behind Claude Code & Codex: constraints, query loops, context governance, multi-agent verification. harness-books.agentway.dev

Python

peteromallet

desloppify

★ 3,158

Agent harness to make your slop code well-engineered and beautiful.

Python

kite-org

kite

★ 3,152

🪁 A lightweight, modern Kubernetes dashboard that unifies multi-cluster and resource management, enterprise-grade user governance (OAuth, RBAC, and audit logs), and AI agents in one workspace. Not just a tool, but more like a platform.

TypeScript

oritera

Cairn

★ 3,149

A AI general-purpose state-space search engine, validated first on autonomous penetration testing.

Python

TanStack

ai

★ 3,149

🤖 Type-safe, provider-agnostic TypeScript AI SDK for streaming chat, tool calling, agents, and multimodal apps across OpenAI, Anthropic, Gemini, React, Vue, Svelte, and Solid.

TypeScript