Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.
| Date | Stars |
|---|---|
| 2026-07-31 | 7704 |
| 2026-08-02 | 7704 |
| 2026-08-04 | 7739 |
| 2026-08-06 | 7739 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
5.0
growth rate 0.00%/day
<div align="center">
<img src="media/header_compress.png" width="800" alt="NVIDIA Isaac GR00T N1.7 Header">
<!-- --- -->
<p style="font-size: 1.2em;">
<a href="https://developer.nvidia.com/isaac/gr00t"><strong>Website</strong></a> |
<a href="https://huggingface.co/collections/nvidia/gr00t-n17"><strong>Model</strong></a> |
<a href="https://huggingface.co/collections/nvidia/physical-ai"><strong>Datasets (Physical AI)</strong></a> |
<a href="https://arxiv.org/abs/2503.14734"><strong>Paper</strong></a> |
<a href="https://developer.nvidia.com/isaac"><strong>NVIDIA Isaac</strong></a> |
<a href="FAQ.md"><strong>FAQ</strong></a>
</p>
</div>
## Table of Contents
- [NVIDIA Isaac GR00T](#nvidia-isaac-gr00t)
- [What's New in GR00T N1.7](#whats-new-in-gr00t-n17)
- [Installation](#installation)
- [LeRobot Integration](#lerobot-integration)
- [Model Checkpoints & Embodiment Tags](#model-checkpoints--embodiment-tags)
- [Data Format](#data-format)
- [Inference](#inference)
- [Fine-tuning](#fine-tuning)
- [Evaluation](#evaluation)
- [Contributions](#contributions)
- [License](#license)
- [Citation](#citation)
---
## NVIDIA Isaac GR00T
<table style="width:100%; table-layout:fixed;">
<tr>
<td style="width:33.33%; text-align:center;">
<img src="media/unitree_g1.gif" style="max-width:100%; height:auto;">
</td>
<td style="width:33.33%; text-align:center;">
<img src="media/agibot_g1.gif" style="max-width:100%; height:auto;">
</td>
<td style="width:33.33%; text-align:center;">
<img src="media/yam.gif" style="max-width:100%; height:auto;">
</td>
</tr>
</table>
> We just released GR00T N1.7 General Availability, the latest version of GR00T N1 with a new VLM backbone (Cosmos-Reason2-2B / Qwen3-VL) and improved performance.
> **This is a General Availability (GA) release.** You are welcome to download the model, explore the codebase, and build on the stack, with full support and stability guarantees.
>
> **What's available:**
> - Pre-trained GR00T N1.7 model weights and reference code
> - Fine-tuning and inference with custom robot data or demonstrations
> - Experimentation, prototyping, and research use cases
> - Production deployment with commercial support
> - Complete benchmarks and a fully validated, stable feature set
> - Pull request contributions
>
> We welcome feedback - please feel free to raise issues and pull requests in this repository.
> Previous releases: [N1.6](https://github.com/NVIDIA/Isaac-GR00T/tree/n1d6) | [N1.5](https://github.com/NVIDIA/Isaac-GR00T/tree/n1d5)
NVIDIA Isaac GR00T N1.7 is an open vision-language-action (VLA) model for generalized humanoid robot skills. This cross-embodiment model takes multimodal input, including language and images, to perform manipulation tasks in diverse environments.
GR00T N1.7 is trained on a diverse mixture of robot data including bimanual, semi-humanoid and an expansive humanoid dataset. It is adaptable through post-training for specific embodiments, tasks and environments.
GR00T N1.7 is fully commercially licensable under Apache 2.0. It delivers comparable performance to N1.6, with improved generalization and language-following capabilities driven by the inclusion of 20K hours of EgoScale human video data in pretraining.
The neural network architecture of GR00T N1.7 is a combination of vision-language foundation model and diffusion transformer head that denoises continuous actions. Here is a schematic diagram of the architecture:
<div align="center">
<img src="media/model-architecture.png" width="800" alt="model-architecture">
</div>
### Workflow Overview
1. **Prepare data** — Collect robot demonstrations (video, state, action) and convert them to the [GR00T LeRobot format](#data-format). Demo datasets are included for quick testing.
2. **Run inference** — Try zero-shot inference with the base model on [pretrain embodiments](#embodiment-tags), or use a [finetuned checkpoint](#checkpoints) for benchmaExcerpt of 35,083 characters
Read on GitHub
youliang · Nvidia · United States
33
20
16
7
7
4
4
Sean Gillen
3
2
Tao Li · Nvidia · China
2
2
2
2
2
1
1
1
Silvio Traversaro · Generative Bionics @gbionics
1
Yiheng Wang · Nvidia
1
yuyoujiang
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:fa4b0198658d1b60, llm:Repository description: 'NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.' (NVIDIA Isaac GR00T is a foundation model for generalist robots).
matched fp:fa4b0198658d1b60, llm:Repository description: 'NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.' (NVIDIA Isaac GR00T is a foundation model for generalist robots).
matched fp:fa4b0198658d1b60, llm:Repository description: 'NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.' (NVIDIA Isaac GR00T is a foundation model for generalist robots).