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

2,665–2,688 of 3,685

husu

loom

★ 534

一个写接口文档的AI Agent。支持使用Vibe coding 的方式，编写接口文档，同时自带友好的文档查看工具与接口Mock工具

nirholas

XActions

★ 534

⚡ The Complete X/Twitter Automation Toolkit — Scrapers, MCP server for AI agents (Claude/GPT), CLI, browser scripts. No API fees. Open source. Unfollow people who don't follow back. Monitor real-time analytics. Auto follow, like, comment, scrape, without API. Follow Bot. Like bot. Grow your account automatically.

HTML

stablyai

agent-slack

★ 534

Slack automation CLI for AI agents

TypeScript

vibeeval

vibecosystem

★ 534

AI software team for Claude Code - 138 agents, 295 skills, 73 hooks. Self-learning, multi-agent swarm, autonomous skill evolution.

concierge-hq

concierge

★ 532

🚀 Universal SDK for building next-gen MCP servers

Python

DannyMac180

skills

★ 532

AI agent skills created by me: Dan McAteer

JavaScript

decionis

agent-safe-pipeline

★ 532

Reference architecture for AI agents that propose actions but cannot authorize them — immutable intent capture, an independent Decionis policy verdict (ALLOW/ESCALATE/BLOCK), verified human approval, and a SafeExecutor that consumes a single-use intent-bound grant.

TypeScript

ooples

token-optimizer-mcp

★ 531

Measure token savings per AI coding agent, optimize context, and share a live local knowledge graph across 16 CLI clients.

JavaScript

ImKKingshuk

LockKnife

★ 530

LockKnife: The Ultimate Android Security Research Tool. A unified TUI workspace and headless CLI for deep Android security research, built for researchers and hackers. Powered by Python orchestration and a Rust-accelerated core, enabling AI agent–driven hacking, credential recovery/cracking, APK analysis, intelligence gathering, runtime inspection.

Python

l0ng-ai

papr

★ 530

A fast, native RSS reader — plus an agent-facing CLI so your AI agent can read, search and triage your feeds from the shell.

Rust

Tencent

CognitiveKernel-Pro

★ 530

Deep Research Agent CognitiveKernel-Pro from Tencent AI Lab. Paper: https://arxiv.org/pdf/2508.00414

Python

truecourse-ai

truecourse

★ 530

Turns the documentation you already write into tests that run. A failing test means your product and your docs disagree, and names the section.

TypeScript

x-glacier

GenerativeAgentsCN

★ 530

本项目为Generative Agents项目的重构+深度汉化版本，旨在为中文用户提供一个利于维护的基础版本，以便后续实验或功能拓展。

Python

Gnosil

semantix

★ 529

semantic agent kernel which make agent efficient and self-evolve

helloianneo

ian-xiaohei-scenes

★ 529

Xiaohei 2.0 Codex Skill for Chinese real-object article illustrations and long-scroll story images

ARCANGEL0

EVA

★ 527

EVA is an AI-assisted penetration testing agent that enhances offensive security workflows by providing structured attack guidance, contextual analysis, and multi-backend AI integration.

Python

BOMWiki

partmode

★ 527

Open-source, local-first 3D parametric CAD that runs in the browser for people and permissioned typed agents, powered by OpenCascade WASM.

JavaScript

my-claude-utils

clsh

★ 527

Access your terminal and your AI agent from any device — phone, tablet, desktop.

TypeScript

tjxj

z-skills

★ 527

A collection of reusable skills

Python

antibrow

★ 526

Kernel-level antidetect browser with the Playwright API you already write. Python + Node SDKs, MCP-ready, unlimited local profiles. Linux x64 + arm64, macOS Intel + Apple Silicon, Windows x64.

TypeScript

koloai

kolo

★ 526

Kolo is a text-based Python debugger for AI agents. Capture every executed function call, return value, local variable, HTTP request, and more in greppable trace files.