SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.

The Destructive Command Guard (dcg) is for blocking dangerous git and shell commands from being executed by agents.

QuickJS, the Next Generation: a mighty JavaScript engine

CLI to manage emails

open-arms-mini: cheap human like teleoperation device that supports human in the loop corrections

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

Open source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for multitasking, organization, and programmability.

Standard Open Arm 100

Unified framework for robot learning built on NVIDIA Isaac Sim

Multi-Joint dynamics with Contact. A general purpose physics simulator.

Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference

MCP server for controlling Bambu Lab 3D printers — multi-printer fleet management, print control, file ops, AMS, camera, and more

Connects MCP to major 3D printer APIs (Orca, FULU's Orca/Bambu, OctoPrint, Klipper, Duet, Repetier, Prusa, Creality). Control prints, monitor status, and perform advanced STL operations like scalin…

Deterministic browser automation. Works out of the box with Claude/Codex/OpenCode

Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.

The agent that grows with you

Give your agents the power of the Hugging Face ecosystem

Optimize prompts, code, and more with AI-powered Reflective Optimization

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

IronClaw is an Agent OS focused on privacy, security and extensibility

Examples using MLX Swift

⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more

A minimal, secure Python interpreter written in Rust for use by AI

Puffing up reinforcement learning

Our library for RL environments + evals

Algorithm powering the For You feed on X

Claude code setup as an RLM scaffhold Implemented by Brainqub3

Claude Code skill for handling long-context tasks through recursive decomposition

GPU-native composable analytics engine