Highlights
- Pro
Starred repositories
Offline NVIDIA Blackwell VBIOS editor.
Ultra-Efficient Humanoid Control with Differentiable Simulation.
Humanoid whole-body motion tracking with one differentiable world model.
Agentic AI for robotics: an LLM agent writes the vision-based controller for a humanoid hand (Unitree G1 + Dex3, MuJoCo). 92-100% on unseen layouts and conditions, ~$2.60 per controller.
An agent skill for creating detailed, interactive isometric illustrations of real-world machines and complex systems. Generates polished SVGs with optional WebGL shaders and 3D effects.
Low-level unprivileged sandboxing tool used by Flatpak and similar projects
Local inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus small NPU models, over the OpenAI and Anthropic APIs on one port.
The open-source AI engine for AMD Strix Halo. Text, embeddings, speech, image and video models in one binary, with OpenAI-compatible APIs, caching for coding agents and model extensions. Linux and …
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
Valdrada is a real-time digital twin of New York City built from public data.
SuperDex brings together a purpose-built physics engine, robotics authoring tools, and a scalable reinforcement learning interface in a unified simulation platform, with VR-based teleoperation and …
SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
sparkrun - launch, manage, and stop LLM inference workloads on NVIDIA DGX Spark systems. Live support: https://discord.com/invite/GH5kRgv6ZD
Docker configuration for running VLLM on dual DGX Sparks
Archived — ML Intern is no longer maintained. Continue with HuggingChat.
A compiler and scenario generator for the Scenic scenario description language.
This is a repository for reinforcement learning implementation for Unitree robots, based on Mujoco.
Create beautiful slides on the web using a coding agent's frontend skills