AI channel
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

2,617–2,640 of 4,275
Katakate

k7

★ 810

Your own self-hosted infra for lightweight VM sandboxes to safely execute untrusted code. CLI, API, Python SDK. ⭐ Star it if you like it! ⭐

Python
risa-labs-inc

BossConsole

★ 809

Open-source, multi-platform harness for AI agents - a native, multi-threaded operator's console (JVM, not Electron) to run Claude Code, Codex, Gemini or OpenCode with a real browser, terminal, editor, secrets & 100+ MCP tools. Built for enterprises, science & research.

Kotlin
Haohao-end

openagent

★ 807

What if OpenAI Deep Research and Dify were one platform? OpenAgent — harness architecture for rapidly building vertical AI agents, with deep reasoning loops, visual workflows, RAG, and A2A delegation.

Python
Unclecheng-li

poc-lab

★ 807

Recent CVE PoC & reproduction scripts. Focused on high-severity vulnerabilities across Linux kernel, Windows, macOS and more.

C
A-EVO-Lab

a-evolve

★ 805

The official repository of "Position: Agentic Evolution is the Path to Evolving LLMs".

Python
★ 804

BioMate-KB Bioconductor Skills — 200 packages (top 100 by downloads + 100 rising stars) as vignette-grounded Claude/agent skills, with per-package workflow recipes

Python
★ 804

A local-first desktop workspace for running, organizing, and resuming multiple coding agents and shells with real PTYs, split panes, persistent layouts, and local session history.

TypeScript
christopherkarani

Wax

★ 803

Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple Silicon.. No Server. No API. One File. Pure Swift

Swift
FrancescoStabile

numasec

★ 803

The AI Agent for Cyber Security.

TypeScript
Purewhiter

mobilegym

★ 803

[EMNLP 2026] MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research · 浏览器里运行的安卓模拟器 · Browser-hosted Android Simulator · Verifiable Evaluation · Scalable Online RL Training

Python
ra1nty

DXcam

★ 803

A Python high-performance screen capture library for Windows using Desktop Duplication API - Updated 2026

Python
★ 802

Talk to research papers like talking to authors - Python package with AI agent for arXiv papers

Python
★ 801

RocketSim — 30+ tools for Xcode's iOS Simulator. Testing, debugging, network monitoring, captures, accessibility, app actions, and AI agent automation via the RocketSim CLI. Used by 80k+ developers.

Swift
juanceresa

sift-kg

★ 801

Turn any collection of documents into a knowledge graph. Extract entities and relationships via LLM, deduplicate with your approval. Map domains, find hidden connections, spot patterns across documents — knowledge that persists and compounds, for you and your AI agents. All from the CLI.

Python
kgoedecke

doop

★ 800

The open-source alternative to Paper.design. A multiplayer design canvas where humans and AI agents design together, live. MCP built in.

TypeScript
Optim-Agent

optim-agent

★ 800

LLM agents as your hyperparameter optimizer.

Python
★ 798

Codex skill for removing defensive writing and strengthening prose.

PowerShell
★ 797

A test runner for agentskills.io-style AI agent skills

TypeScript
★ 797

OpenClaw Supermemory lets to have long-term memory and recall for your openclaw agent.

TypeScript
regent-vcs

re_gent

★ 796

Version control for AI agents — track what your agent did, blame any line to a prompt, inspect any step.

Go
★ 796

An AI agent that can get things done across iPhone apps.

Swift
thedivergentai

GD-Agentic-Skills

★ 794

The official "Long-Term Memory" for Godot 4.7+ AI Agents. A high-density library of 99 expert skills and 27 genre blueprints, providing audited, strictly typed GDScript patterns, automated persona orchestration (Analyst, Auditor, Builder), and production-grade game engineering.

GDScript
traceroot-ai

traceroot

★ 794

TraceRoot - open-source observability and self-improving layer for AI agents. YC S25

TypeScript
coder

boo

★ 793

A GNU screen style terminal multiplexer built on libghostty.

Zig