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

3,073–3,096 of 3,720

growthxai

output

★ 438

The open-source TypeScript framework for building AI workflows and agents. Designed for Claude Code describe what you want, Claude builds it, with all the best practices already in place.

JavaScript

heygen-com

skills

★ 438

HeyGen AI agent skills — avatar creation and video production via the v3 Video Agent pipeline

Shell

leopard627

fire-your-seo-agency

★ 438

Fire your SEO·GEO agency 🔥 A Claude Code skill that audits and optimizes SEO·AEO·GEO·LLMO·NEO(Naver) by itself — 월 50~350만 원짜리 'AI 검색 최적화' 대행, AI 에이전트가 대체합니다

adithyan-ak

AgentHound

★ 437

Offensive security framework for AI agent infrastructure - recon, credential looting, model exfiltration, poisoning, and attack-path analysis across MCP, A2A, gateways, and AI services. BloodHound for the agentic stack.

aoci-spec

aoci-code

★ 437

Distills code and database knowledge into a persistent, governed map of the entire repository—helping AI coding agents understand complex systems faster and carry development forward with greater precision.

minthcm

★ 437

Open-source HCM system for managing HR processes with AI agents. Full data ownership, MCP/A2A-native, no vendor lock-in.

PHP

Prysai

Prysai-LLM-Playbook

★ 437

An evidence-led, eight-locale LLM playbook: a transferable core, the Codex flagship track, and adapters for ChatGPT, Claude Code, Gemini, DeepSeek, and Grok.

Python

HalfAI1102

anthropic-art

★ 436

Generate full-background Anthropic-style editorial illustrations with verified palette and hand-drawn visual rules.

rollingSirius

equity-research-skill

★ 436

Possibly the deepest AI equity-research skill: nine-chapter single-stock deep dives and earnings deep-dives, with scripted DCF/EPV/EVA and reproducible valuation. Covers US, HK and A-shares. Docs in EN and ZH.

Python

Ancienttwo

repo-harness

★ 435

File-backed workflow harness for reliable Claude Code and Codex sessions.

TypeScript

apm-studio

★ 435

Local editor for importing, managing, running, and injecting APM-backed assistant packages.

TypeScript

Jia-Ethan

★ 432

A runtime for agents and services

tongjingqi

AI-Can-Learn-Scientific-Taste

★ 432

We propose Reinforcement Learning from Community Feedback (RLCF), a training paradigm that uses large-scale community signals as supervision, and formulate scientific taste learning as a preference modeling and alignment problem.

vintasoftware

django-ai-assistant

★ 432

Integrate AI Assistants with Django to build intelligent applications

Python