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

3,097–3,120 of 4,275

criptogus

HermesOffice

★ 601

AI-native office suite (Docs, Sheets, Slides, PDF) where the Hermes Agent is the brain — open standards, byte-preserving round-trip, 100% local.

TypeScript

minhnv0807

ai-business-skills

★ 601

138 bilingual AI marketing skills (69 VN + 69 Global) for Claude Code, OpenCode, Codex, VS Code. Four role SOP packs — content, design, performance, leader ops — plus strategy, personal brand, AI avatar, dropshipping, design master, knowledge library. 4 regions (US/EU/SEA/LATAM) + Vietnam 2025-2026. Companion: opa-kit.

PowerShell

yliust

Tactile

★ 601

Tactile: an accessibility-first operating layer for agents.

Python

agentara

skills

★ 600

Original and practical skills for AI builders.

HTML

ww-w-ai

bkit-claude-code

★ 600

bkit Vibecoding Kit - PDCA methodology + Claude Code mastery for AI-native development

JavaScript

ianjwhite99

opencode-with-claude

★ 599

OpenCode plugin to use your Claude Max/Pro subscription with OpenCode via Meridian

JavaScript

normal-computing

fuji-web

★ 599

Fuji is an AI agent that lives in your browser's sidepanel. You can now get tasks done online with a single command!

TypeScript

RobotecAI

rai

★ 599

RAI is a vendor agnostic agentic framework for Physical AI robotics, utilizing ROS 2 tools to perform complex actions, defined scenarios, free interface execution, log summaries, voice interaction and more.

Python

smallnest

goclaw

★ 599

An open-source AI assistant framework like openclaw

Yean-Sec

StrikeAgent_AtkBrain-Flash

★ 599

由夜安团队研发的AI渗透测试平台，涵盖红队打点、SRC、CTF，特别是在红队领域有极为亮眼的存在

Python

GMGNAI

gmgn-skills

★ 597

GMGN OpenAPI skills for AI Agent — query tokens, wallets, and market data, and execute on-chain trades across Solana, BSC, and Base.

Python

AMA-CMFAI

LAMBDA

★ 596

This is the offical repository of paper "LAMBDA: A large Model Based Data Agent". https://www.polyu.edu.hk/ama/cmfai/lambda.html

Python

aldefy

compose-skill

★ 595

Jetpack Compose Agent Skill — AI-powered coding guidance with actual androidx/androidx source code receipts. Works with Claude Code, Codex CLI, Gemini CLI, Cursor, Copilot, Windsurf, and more.

Kotlin

howmp

dsh-pentest

★ 594

面向 DeepSeek Harness（dsh）的渗透测试模式 @CloverSecLabs

JavaScript

LayrKits

Sprite-Pipeline

★ 594

2D Sprite Sheet Creation Pipeline

Python

run-llama

ParseBench

★ 594

ParseBench - A Document Parsing Benchmark for AI Agents

Python

viticci

remctl

★ 594

An Apple Reminders CLI for power users and AI agents. RemCTL supports all the latest Reminders features such as sections, subtasks, tags, rich links, groceries lists, templates, smart lists, and image attachments. (Not affiliated with Apple.)

Python

awslabs

fullstack-solution-template-for-agentcore

★ 593

Flexible Fullstack solution template for production-ready deployments of any use case on Amazon Bedrock AgentCore.

Python

FradSer

dotclaude

★ 593

A comprehensive development environment with specialized AI agents for code review, security analysis, and technical leadership.

JavaScript

winstonkoh87

Athena-Public

★ 593

Athena is a local-first agentic PKM that helps you make better decisions with your own context — persistent memory, structured reasoning, and governed AI agents that work across any LLM. Own the state. Rent the intelligence.

Python

sharpdeveye

maestro

★ 592

Workflow fluency for AI coding agents. 1 core skill · 25 commands · 7 domain references · memory layer · audit trail — works across Cursor, Claude Code, Gemini CLI, Copilot, and 6 more.

TypeScript