Orchestrate thousands of agents and harnesses as a graph programatically

Browser automation CLI for AI agents

Rust-native hybrid training & inference engine for Apple Neural Engine + Metal GPU

Damn Vulnerable MCP Server Project

Vite plugin that reimplements the Next.js API surface — deploy anywhere

Open-source orchestration for zero-human companies

The web browser built for scraping

Shannon Lite is an autonomous, white-box AI pentester for web applications and APIs. It analyzes your source code, identifies attack vectors, and executes real exploits to prove vulnerabilities bef…

Open-source Agent Operating System

OpenClaw-RL: Train any agent simply by talking

Bootstraps a fresh Ubuntu VPS into a complete multi-agent AI development environment in 30 minutes: coding agents, session management, safety tools, and coordination infrastructure

omo; the best agent harness - previously oh-my-opencode

All parts of Claude Code's system prompt, 24 builtin tool descriptions, sub agent prompts (Plan/Explore/Task), utility prompts (CLAUDE.md, compact, statusline, magic docs, WebFetch, Bash cmd, secur…

Fast, small, and fully autonomous AI personal assistant infrastructure, ANY OS, ANY PLATFORM — deploy anywhere, swap anything 🦀

High-speed rs private server built automation first

X/Twitter research skill for Claude Code and OpenClaw. Agentic search, thread following, deep-dives, sourced briefings.

Runescape automation library, optimized for use by coding agents.

Creative cellular automata browser game

Ralph is an autonomous AI agent loop that runs repeatedly until all PRD items are complete.

Client source port to TypeScript

IsoCity: City building simulation game.

Cataclysm - Dark Days Ahead. A turn-based survival game set in a post-apocalyptic world.

An interactive web-based demonstration of fundamental tabular Reinforcement Learning (RL) algorithms in a simple grid world environment.

The open-source, canonical implementation of Farcaster's Snapchain network.

The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement …

Puffing up reinforcement learning

Food chain simulator, as described in this video! https://www.youtube.com/watch?v=Zy9N48udcdc

crypto twitter's finest, real OGs subjectively curated by raz in 2025