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

3,577–3,600 of 3,726

kelos-dev

kelos

★ 326

Kelos - The Kubernetes-native framework for orchestrating autonomous AI coding agents.

kunchenguid

kun

★ 326

Think and build like a principal engineer. Leverage Kun's experience, knowledge, tools, workflows, and skills to help you get shit done.

kunchenguid

vision

★ 326

Agent skill that mines your repo's history to draft a VISION.md, stress-tests it with hard hypotheticals, and iterates with you on an interactive review board.

HTML

MaySudo

Misceo

★ 326

Local Anthropic-compatible AI gateway with cheap-first routing, quality gates, safe model handoffs, and an embedded cost dashboard.

rengwu

chartr

★ 326

Agent multiplexer with spaces, panes, and plugins

rwjdk

agent-framework-samples

★ 326

Samples demonstrating the Microsoft Agent Framework in C#

huisezhiyin

sdd-riper

★ 325

Lightweight AI Agent Harness for agentic coding: let strong models explore while humans steer with minimal specs, checkpoints, approval, validation, and reverse sync.

Python

inhouseseo

superseo-skills

★ 325

11 Claude skills for SEO: page audits, linkbuilding, article writing, E-E-A-T audits, semantic gap analysis, link building. Methodology from Koray Tuğberk, Kyle Roof, and Lily Ray, plus a generation-time anti-AI-slop ruleset. Production-tested at InhouseSEO

mahimairaja

voiceai

★ 325

Set of 📝 with 🔗 to help those building Voice AI agents 🎙️🤖

rixinhahaha

snip

★ 325

The visual communication layer between humans and AI agents. Capture, annotate, render diagrams, and organize with AI — powered by Electron and Ollama. macOS & Linux.

JavaScript

shengsheng90

DSH-taskboard

★ 325

Native local Taskboard plugin for DeepSeek Harness. SQLite-backed projects, Agent claim/review, and a native Web UI — no iframe, no second chat runtime.

TypeScript

kris-hansen

comanda

★ 324

The CLI-native orchestrator for AI agent workflows. Run Claude Code, Codex, Gemini CLI & Kimi Code from declarative YAML. Because the terminal is where real work happens.

linkerlin

PUAX

★ 324

用来驯服AI Agent的效果绝佳的多角色 Prompt SKILLs！

TypeScript

yee-yore

DorkAgent

★ 324

🤖 LLM-powered agent for automated Google Dorking in bug hunting & pentesting.

Python

0xranx

golembot

★ 323

Any Agent × Any Provider × Anywhere. Connect Cursor, Claude Code, OpenCode, or Codex to Slack, Telegram, Discord, Feishu, DingTalk, WeCom, WeChat — with any LLM provider.

TypeScript

bibinprathap

VeritasGraph

★ 323

VeritasGraph — open-source Knowledge Graph & GraphRAG framework on GitHub. Build multi-hop reasoning, ontology-aware retrieval, and verifiable attribution over your own data. Nodes, edges, RDF, linked-data — runs locally or in the cloud.

Python

Encod3d-Sec

TORCH

★ 323

Karpathy LLM based claude harness for PenetrationTesting / Bugbounty using obsidian

Python

JetBrains

benjamin-plus-skill

★ 323

Benjamin-Plus: a measured token-efficiency skill for coding agents (−17.9% cost median, quality unchanged). Inject it, don't install it.

Shell

railwayapp

railway-skills

★ 323

Agent skills for interacting with Railway

Python

rush-db

rushdb

★ 323

RushDB is a graph + vector database and memory layer for AI agents. Push any JSON, get typed, searchable, relationship-aware records back — no schema, no migrations. Built on Neo4j.

TypeScript

superagents-lab

xcode27-skills

★ 323

Apple's official Agent Skills exported from Xcode 27 — SwiftUI, UIKit modernization, Swift Testing, C bounds-safety, and security hardening for AI coding agents.

Python