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

3,025–3,048 of 3,708

AI-Native 工程师招聘面试官手册 · Builder / Reviewer 双岗评分 · AI 驾驶能力实操考核 · 易哈佛医疗

HTML
agentverse-os

AgentVerse-OS

445

Personal cloud OS for a developer and their AI agents on a single server. One-command install on Ubuntu, then everything in the browser: a windowed desktop, isolated workspaces with VS Code, Claude Code and Codex, a store of 944 self-hosted apps, backups and updates. Access only via Tailscale, nothing exposed to the internet. Rust core, Svelte UI.

Rust
Dicklesworthstone

ntm

445

Named Tmux Manager: spawn, tile, and coordinate multiple AI coding agents (Claude, Codex, Gemini) across tmux panes with a TUI command palette

Go
frenzymath

Danus

445

Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory

Python
secondsky

sap-skills

445

Production-ready plugins for SAP development with AI coding assistants — BTP, CAP, Fiori, ABAP, HANA, Analytics Cloud, Datasphere, and more

JavaScript
Beever-AI

beever-atlas

444

Your First LLM-Wiki Conversation Knowledge Base

Python
chr15m

runprompt

444

Run LLM prompts from your shell

Python
qingchencloud

clawapp

444

📱 ClawApp — OpenClaw AI 智能体手机聊天客户端 | 流式对话 · 图片收发 · 工具调用 · PWA + APK | Mobile chat client for OpenClaw AI Agent

JavaScript
docwriter-org

plain-writing-skill

443

A plain-language writing skill for AI agents, with a revision view that shows what changed.

Python
MirroS-Lab

Code-as-World

443

Code as World: Agentic Discovery of Executable World Representations for Physical Reasoning

Python
professorpalmer

Puppetmaster

443

Provider-neutral control plane for durable-state agent swarms: subprocess workers, leases, artifacts, memory, and deterministic stitching.

Python
ApodexAI

AgentHarness

442

Evaluation harness for Apodex-1.0 on public deep-research benchmarks.

Python
442

Python toolkit for building graph-enhanced GenAI applications

Python
axislab-top

Foundry

442

Transform any idea into a running AI-powered company

TypeScript
chattymin

PokeTokenBar

442

Use your tokens to raise, evolve, and collect Pokémon! 🥚

Swift
intellicia-public

parastore

442

Draw a store, generate LLM personas, and watch them shop — an isometric 3D sandbox for synthetic-consumer experiments.

TypeScript
boshu2

agentops

441

The operations layer for agentic engineering — portable skills and contracts connecting intent, agents, software factories, and independent judgment.

Go
441

AI-powered contract review skill with CUAD risk detection, market benchmarks, and lawyer-ready redlines. Works with Claude Code, Codex, Cursor, and 26+ tools.

Ariescar

anyCreature

440

You can now generate creatures directly within your project. Drop the open-source into your Agent, and start prompting what you want.

JavaScript
baskduf

FableCodex

440

🗿 FableCodex is a Codex-style coding agent workflow that plans like Fable.

Python
dolag233

Serpent

440

Cross-platform digital asset management software for game artists, VFX professionals, and graphic and motion designers.

TypeScript
440

An AI Agent that interacts with Windows OS at GUI level.

Python
Jia-Ethan

grok-keysmith

440

Preview-first Grok Build instruction deployment with compat and hook isolation, durable recovery, and layered uninstall.

Python
kharmanskyi

open-steps

440

Skills that translate your coding agent's output into plain language: honest reports, straight verdicts, steps you can follow. MIT.

Shell