Muon is an optimizer for hidden layers in neural networks

Customizable Reinforcement Learning

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…

SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning

Efficient, reusable RNNs and LSTMs for torch

VQVAEs, GumbelSoftmaxes and friends

vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization

KDE Plasma Desktop container designed for Kubernetes, supporting OpenGL EGL and GLX, Vulkan, and Wine/Proton for NVIDIA GPUs through WebRTC and HTML5, providing an open-source remote cloud/HPC grap…

An open-source, GPU-accelerated physics simulation engine built upon NVIDIA Warp, specifically targeting roboticists and simulation researchers.

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

Joycon-Robotics: Low-Cost, Convenient Teleoperation for One- and Two-Arm Robots

Official code of RDT 2

Pointcept: Perceive the world with sparse points, a codebase for point cloud perception research. Latest works: Sonata (CVPR'25 Highlight), PTv3 (CVPR'24 Oral)

[NeurIPS'25] The official code of "PeRL: Permutation-Enhanced Reinforcement Learning for Interleaved Vision-Language Reasoning"

Open-source KVM software

VS Code in the browser

Render URDF/MJCF/USD robots instantly in your browser

The VCGlib is a C++, templated, no dependency, library for manipulation, processing and cleaning of triangle meshes

Import a 3D Model and automatically assign and export animations

Implementation of a single layer of the MMDiT, proposed in Stable Diffusion 3, in Pytorch

Connect agent policies for distributed ML applications

Galaxea's first diffusion policy release

Python GUI builder. GUI builder for Tkinter, CustomTkinter, Kivy and PySide (upcoming)

Repository for Paper "Analyzing Key Objectives in Human-to-Robot Retargeting for Dexterous Manipulation"

Code for Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes (Science Robotics)