Stars
Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse environments
OpenClaw Plan→Work→Review workflow engine with model routing
tmux config with built-in terminal automation and agent-to-agent communication.
Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞
real time face swap and one-click video deepfake with only a single image
A Claude Skill to give your agent the ability to use a web browser
ALIVE Context System -- a living context system for Claude Code. The successor to PARA. Your life in walnuts.
Dead-simple Bun CLI that runs Codex and Claude Code in a loop.
Container runtimes on macOS (and Linux) with minimal setup
Give AI coding agents eyes. Records browser sessions, captures screenshots, collects errors, and bundles proof artifacts — so humans can verify what the agent built.
Build and run agents you can see, understand and trust.
Skills for the Gemini API, SDK and model/agent interactions
Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.
Open-source orchestration for zero-human companies
tiny AI companions that live on your macOS dock
Memento-Skills: Let Agents Design Agents
the best interface for Claude Code
A lightweight web dashboard for viewing all your OpenClaw Bots/Agents/Models/Sessions status at a glance.
Complexity within, simplicity without. 繁于内，简于形。
For people who get distracted by agents. A native Rust/GPUI control plane for running Claude Code, Codex, Cursor, and OpenCode side by side — because if you're going to be squirrely, you might as w…
ClawTeam: Agent Swarm Intelligence (One Command → Full Automation)
Minimal kernel to make any AI coding agent stateful. Clone, point your agent, go.
TradingAgents: Multi-Agents LLM Financial Trading Framework
Allow all your Claude Codes to message each other ad-hoc!