Unified Implementations of Offline Reinforcement Learning Algorithms

An interactive HTML pretty-printer for machine learning research in IPython notebooks.

RL training library for humanoid locomotion and manipulation. Built on top of MuJoCo and JAX.

Multi-platform high-performance compute language extension for Rust.

[CoRL 2025] Neural Robot Dynamics

Thermodynamic Hypergraphical Model Library in JAX

Voice-to-text with push-to-talk for Wayland compositors

A lightweight suite of motion imitation methods for training controllers.

Simplifying reinforcement learning for complex game environments

Machine Learning Research Flashcards (for Anki)

ProtoMotions is a GPU-accelerated simulation and learning framework for training physically simulated digital humans and humanoid robots.

RL training visualizer for Mujoco Playground environments + Brax training

Cursor Agent ACP Adapter

SGLang is a high-performance serving framework for large language models and multimodal models.

🧑‍🎨 Mobile app for drawing 2D animations

PKM Markdown Language Server

A scalable asynchronous reinforcement learning implementation with in-flight weight updates.

Community-driven Nix Flake for the Zen browser

Shimeji reimplementation for Wayland in C

Code for "PHUMA: Physically-Grounded Humanoid Locomotion Dataset"

Loading Safetensor from HF to Equinox

Wayland Speech-to-Text Tool - A minimal signal-driven speech-to-text tool for Wayland environments with PipeWire audio

Real-Time Transcription System for Niri - MacOS-like dictation for Linux Wayland environments

Isaac Lab API, powered by MuJoCo-Warp, for RL and robotics research.

Is Temporal Difference Learning the Gold Standard for Stitching in RL? Code repository for research paper.

[ICRA 2026] Official implementation of the paper "GSWorld: Closed-Loop Photo-Realistic Simulation Suite for Robotic Manipulation"

Git powered terminal-based todo/note manager -- markdown note page per task. Single binary!

Rust actor framework