NVIDIA and Hugging Face are integrating NVIDIA's advanced robotics AI models, including Isaac GR00T 1.7 and Isaac Teleop

NVIDIA and Hugging Face have announced a collaboration to integrate NVIDIA's robotics capabilities into LeRobot, Hugging Face's open source robotics library. The partnership brings the NVIDIA Isaac GR00T 1.7 open reasoning vision language action model for humanoid robots and the NVIDIA Isaac Teleop framework to LeRobot, with NVIDIA Cosmos 3, a frontier model for physical AI, planned for future integration. Together, these tools provide developers with a more accessible and standardized path for end-to-end robot development while fostering innovation across the open robotics community.

Thomas Wolf, cofounder and chief science officer at Hugging Face, emphasized that open source transforms advanced research into something developers can study, adapt and build upon. With these integrations, robotics developers can now use shared models, data and workflows to train and evaluate robots collaboratively, and will soon have access to frontier world models through the same open loop.

LeRobot is an open source library designed for training, running and sharing robot datasets, models, policies and workflows. This partnership connects NVIDIA's 3 million robotics developers with Hugging Face's 16 million AI builders, significantly expanding access to frontier physical AI tools through open workflows. The integrations enable developers to collect and standardize data, train and fine-tune robot foundation models, evaluate performance and deploy models through shared open workflows. The collaboration builds on existing NVIDIA resources already connected to LeRobot to support the complete robotics development pipeline.