# Isaac GR00T — weights, license and what is actually open

An open vision-language-action model for generalized humanoid skills, accompanied by reference code, data tooling, and a robotics development stack.

Canonical: https://brightaifuture.com/open-models/groot
Format: model-family
Source publication: Not established
Bright publication: 2026-09-19
Substantive update: None recorded
Evidence and review: AI-assisted primary-source check on 2026-09-19; no independent model reproduction or license certification. The original GR00T N1 paper provides research evaluation; N1.7 deployment claims remain primarily NVIDIA-reported.

## Documented release

GR00T N1.7

Organization: NVIDIA

GR00T N1.7 early-access release: 2026-04-18 (day precision). Source: https://github.com/NVIDIA/Isaac-GR00T/releases

The cited official release is labelled early access; this record does not imply a later general-availability date.

Parameters: Not stated in the reviewed N1.7 overview

Architecture: Vision-language-action foundation model combining perception, language instruction, and robot action generation.

Modalities: text, image, video, robot state, robot action

Context: Not established as a language-token context window in the reviewed release.

## License and commercial use

NVIDIA Open Model License / repository-specific terms

Review the model and data licenses for the intended robot, dataset, and deployment.

## What is open

Weights: available. Pre-trained N1.7 weights are linked from the official repository. Source: https://github.com/NVIDIA/Isaac-GR00T

Architecture: available. The VLA architecture and interfaces are documented. Source: https://github.com/NVIDIA/Isaac-GR00T

Inference code: available. Reference inference and robot integration code is public. Source: https://github.com/NVIDIA/Isaac-GR00T

Training code: available. Fine-tuning and training utilities are public. Source: https://github.com/NVIDIA/Isaac-GR00T

Training recipe: partial. Training and fine-tuning procedures are documented, but full-scale reproduction depends on diverse robot data. Source: https://github.com/NVIDIA/Isaac-GR00T

Data information: available. Embodiments and dataset sources are documented. Source: https://github.com/NVIDIA/Isaac-GR00T

Training data: partial. Substantial open robotics datasets are provided, but not every source used is represented as one corpus. Source: https://github.com/NVIDIA/Isaac-GR00T

Evaluation: partial. Technical evaluations are published; real-world transfer remains platform-dependent. Source: https://github.com/NVIDIA/Isaac-GR00T

Commercial use: partial. NVIDIA permits commercial use under its model terms; dataset-specific permissions remain separate. Custom terms do not by themselves prohibit commercial use. Source: https://github.com/NVIDIA/Isaac-GR00T

## Uses and strengths described in sources

Humanoid manipulation

Cross-embodiment fine-tuning

Open robotics tooling

## Hardware and quantization

Hardware requirements vary by robot platform and inference stack; no universal minimum is asserted.

Deployment formats are hardware- and runtime-specific

## Independent evidence

The original GR00T N1 paper provides research evaluation; N1.7 deployment claims remain primarily NVIDIA-reported.

## Limitations

Robot results depend on hardware, calibration, and safety controls

Real-world operation needs physical safeguards

## Provenance and history

{}

## Original sources

- [Isaac GR00T N1.7 release](https://github.com/NVIDIA/Isaac-GR00T/releases)
- [Isaac GR00T repository](https://github.com/NVIDIA/Isaac-GR00T)
- [Isaac GR00T platform](https://developer.nvidia.com/isaac/gr00t)

## Continue exploring

- [Open Models](https://brightaifuture.com/open-models)
- [Open intelligence thread](https://brightaifuture.com/threads/open)
- [A shared starting point for humanoid skills](https://brightaifuture.com/discoveries/groot-humanoid-skills)