
Open-source runtime where a queen agent builds colonies of parallel workers
- Open source
- Open-source agent
- 11.2K GitHub stars
- Multi-agent frameworks

Open-source runtime where a queen agent builds colonies of parallel workers

Run a pixel-art office of coding agents on subscriptions you already pay for

Strands toolkit with a ready agent harness, sandbox and evals in Python and TypeScript

Google's open-source Go toolkit for building and deploying AI agents

Framework giving agents identity, A2A communication and payments

Open-source evolutionary coding agent that mutates programs against a score you define

Python framework for building autonomous and traditional AI agents

TypeScript multi-agent runtime with durable approvals and verifiable run records

Open-source Python framework for building and orchestrating multi-agent AI systems

Open-source terminal agent that runs on your machine with any model

MCP-native agent framework and CLI that works with most model providers

Open-source SRE agent that investigates production incidents and finds root causes

Continuity layer that keeps one unit of work moving across different agents

Loop that lets Claude Code or Codex CLI run a 14-role AI company on its own

Always-on Claude Code with a real browser on a cheap VPS you control

Browser agent that picks from a page's real controls and cites its sources

Local CLI that lets agents research social platforms through your signed-in Chrome

Autonomous web testing agent that checks functionality, performance, UX and security

Open-source Chrome extension that automates the browser from plain-language instructions

Local UI where a decision model steers a social research CLI and writes a cited report

Prebuilt and custom agents that run on small, fast decision models

Self-hosted AI agent team that makes videos, drives browsers and works a task board