NVIDIA and Hugging Face bring new models and frameworks to LeRobot

The Isaac GR00T platform helps robotics developers scale humanoid data collection and simulation-based training to develop, validate, and deploy policies on real robots. | 7 and the NVIDIA Isaac Teleop framework to LeRobot, Hugging Face’s open-source robotics library.

The companies said they hope to bring NVIDIA Cosmos 3, a frontier model for physical AI, to the platform soon. Isaac GR00T 1.7 is an open, reasoning vision-language-action (VLA) model for humanoid robots. Together, these integrations give developers a more accessible and standardized path for end-to-end robot development while driving innovation and collaboration across the open robotics community. Open-source AI has shown how quickly developers can innovate when models, data, and tools are shared, said the partners. Robotics has the same opportunity, but advancements in physical AI development can still be gated by costly and fragmented resources, from large datasets and robot foundation models to simulation, compute, and validation tools. “Open source is how a field turns advanced research into something people can study, adapt and build on,” said Thomas Wolf, co-founder and chief science officer at Hugging Face. “With NVIDIA Isaac GR00T 1.7 and Isaac TeleOp in LeRobot today, robotics developers can use shared models, data, and workflows to train and evaluate robots in the open. And with NVIDIA Cosmos 3 planned next, the community will have a path to bring frontier world models into that same collaborative loop.” NVIDIA, Hugging Face connect robotics developers with AI builders Hugging Face LeRobot is an open-source robotics library for training, running, and sharing robot datasets, models, policies, and workflows. NVIDIA’s continued partnership with the company connects NVIDIA’s 3 million robotics developers with Hugging Face’s 16 million AI builders, expanding access to frontier physical AI tools through open workflows. Bringing NVIDIA physical AI capabilities into LeRobot gives developers a common way to collect and standardize data, train and fine-tune robot foundation models, evaluate performance, and deploy models through open workflows. The integrations include: NVIDIA Isaac Teleop is an open-source framework for robot data collection, enabling developers to capture high-quality human demonstrations from external devices using standardized, interoperable formats. They can then expand and share datasets with the community, all directly in LeRobot. NVIDIA Isaac GR00T 1.7, the first open and commercially viable robot foundation model, is designed to make it easier to post-train and deploy models through LeRobot workflows. Developers can use it to adapt GR00T to new robot embodiments and tasks with benchmarked performance. NVIDIA Cosmos 3, a frontier world foundation model for physical AI coming soon to LeRobot, can help developers generate and augment robotics data, simulate scenarios, and support policy development when real-world data is limited or too expensive to collect.