Physical AI

# NVIDIA Omniverse

Accelerated libraries and microservices for developing physical AI simulation applications and agentic simulation workflows.

[Start Developing](https://developer.nvidia.com/omniverse)

Overview

## What is NVIDIA Omniverse?

NVIDIA Omniverse™ is a collection of accelerated libraries and microservices for developing [physical AI](https://www.nvidia.com/en-us/glossary/generative-physical-ai.md) simulation applications and agentic workflows. Agents and software developers can use NVIDIA Omniverse™ capabilities as prebuilt tools to build, test, and refine their own solutions and agentic simulation workflows.

### NVIDIA Releases Major Collection of Open Source Agent Tools and Skills for Physical AI

Turn complex robotics, autonomous vehicle, vision AI and industrial digital twin workflows into agent-executable tasks— reducing the costs, time and complexity of building physical AI workflows at scale.

[Read Press Release](https://nvidianews.nvidia.com/news/nvidia-releases-major-collection-of-open-source-agent-tools-and-skills-for-physical-ai)

Technology

## Omniverse Capabilities

[NVIDIA Omniverse libraries](https://developer.nvidia.com/omniverse), microservices, and APIs provide the foundation for data interoperability, scalable GPU-accelerated physics, and physically based rendering. These capabilities can be integrated into applications and services, or called as tools by physical AI simulation agents.

### OpenUSD

Universal Scene Description ([OpenUSD](https://www.nvidia.com/en-us/glossary/openusd.md)) enables interoperable 3D and data simulation workflows, including [SimReady](https://www.nvidia.com/en-us/glossary/simready.md) assets for simulation-ready digital twins.

[Learn More About OpenUSD](https://developer.nvidia.com/usd)

### Physics and Motion

GPU-accelerated physics libraries built on [NVIDIA PhysX](https://developer.nvidia.com/physx-sdk)® deliver scalable,  USD-native physics for complex simulation, robotics, and industrial digital twin workflows.

[Explore ovphysx Library](https://github.com/NVIDIA-Omniverse/PhysX/tree/main/ovphysx)

### Rendering and Simulation

Sensor simulation and physically-based, real-time rendering libraries built on [NVIDIA RTX](https://www.nvidia.com/en-us/products/workstations/rendering.md)™ help generate synthetic data and simulate physical AI environments at scale.

[Learn More About Sensor RTX](https://blogs.nvidia.com/blog/omniverse-sensor-rtx-autonomous-machines/)

[Explore ovrtx Library](https://github.com/nvidia-omniverse/ovrtx)

### Runtime and Deployment

Optimized data architecture and runtime services support the development, deployment, and scaling of physical AI simulation applications and agentic workflows.

[Explore Omniverse Docs](https://docs.nvidia.com/omniverse/index.html)

Use Cases

## How Omniverse Powers Physical AI Simulation Workflows

See how Omniverse libraries, microservices, and tools support simulation applications, services, and agentic workflows across industrial digital twins, synthetic data generation, robotics, and autonomous vehicle simulation.

1. Industrial Facility Digital Twins
2. Synthetic Data Generation
3. Robot   
   Simulation
4. Autonomous Vehicle Simulation
5. Robot   
   Learning

### Industrial Facility Digital Twins

Leverage Omniverse libraries to develop advanced virtual factory solutions and bring data interoperability, physically based visualization, generative AI, and real-time collaboration to your software.

[Explore the Industrial Facility Digital Twins Use Case](https://www.nvidia.com/en-us/use-cases/ai-for-virtual-factory-solutions.md)

Delta Electronics

### Synthetic Data Generation

Developers can save significant training time and reduce costs by using synthetic data alongside real-world data to create carefully labeled datasets for training multimodal physical AI models. And now, with agent skills powered by [NVIDIA Cosmos](https://www.nvidia.com/en-us/ai/cosmos.md)™, developers can turn coding agents into synthetic data experts for physical AI development.

[Explore the Synthetic Data Generation Use Case](https://www.nvidia.com/en-us/use-cases/synthetic-data.md)

### Robot Simulation

Physical AI-powered robots and robot fleets must autonomously sense, plan, and execute complex tasks in the physical world. These include safely and efficiently transporting and manipulating objects in dynamic, unpredictable environments.

[Explore the Robot Simulation Use Case](https://www.nvidia.com/en-us/use-cases/robotics-simulation.md)

### Autonomous Vehicle Simulation

With [NVIDIA Cosmos](https://www.nvidia.com/en-us/ai/cosmos.md), conditioned on Omniverse physics libraries, simulation developers can enhance their AV simulation workflows with high-fidelity, diverse sensor data and realistic behavior to train perception models and validate the AV software stack.

[Explore the AV Simulation Use Case](https://www.nvidia.com/en-us/use-cases/autonomous-vehicle-simulation.md)

### Robot Learning

Preprogrammed robots struggle with unexpected changes, while AI-driven robots use simulation-based learning to adapt to dynamic environments. This enables them to refine capabilities such as navigation and manipulation, improving performance in a wide range of scenarios.

[Explore the Robot Learning Use Case](https://www.nvidia.com/en-us/use-cases/robot-learning.md)

Agility, Apptronik, Fourier Intelligence, Unitree

[Explore All Use Cases](https://www.nvidia.com/en-us/use-cases.md)

Starting Options

## Ways to Build With NVIDIA Omniverse

### Libraries and Agent Skills

Integrate Omniverse libraries, microservices, and skills into physical AI applications and agentic workflows.

[Explore Libraries](https://developer.nvidia.com/omniverse)

### Blueprints

Jump-start building physical AI solutions with NVIDIA Blueprints.

[Try the Blueprints](https://build.nvidia.com/explore/simulation)

Success Stories

## Physical AI Simulation in Practice

NVIDIA Omniverse is used across the physical AI ecosystem to build simulation applications, generate synthetic data, and support digital twin and robotics workflows.

[More Success Stories](https://www.nvidia.com/en-us/case-studies.md)

[Robotics

### Skild AI: Pioneering Omni-Bodied Intelligence Through Simulation

**Customer:** Skild AI  
 **Products:** NVIDIA Isaac, NVIDIA Omniverse](https://www.nvidia.com/en-us/case-studies/skild-ai.md)

[Manufacturing

### Lightwheel Accelerates Physical AI Development With NVIDIA Simulation and Foundation Models

**Customer:** AgiBot, BYD, ByteDance, Figure, Fourier, Galbot, Geely, Google Deepmind, Zordi  
 **Products:** NVIDIA Isaac, NVIDIA Omniverse](https://www.nvidia.com/en-us/case-studies/lightwheel.md)

[Manufacturing

### Siemens Accelerates Product Development and Innovation With Industrial AI

**Customer:** BMW Group, HD Hyundai, Maserati  
 **Products:** NVIDIA Omniverse, NVIDIA Metropolis, NVIDIA AI Blueprint for Video Search and Summarization, NeMo Retriever, NIM](https://www.nvidia.com/en-us/case-studies/siemens-accelerates-product-development-and-innovation-with-industrial-ai.md)

Ecosystem

## Industry Leaders Adopt Omniverse

Resources

## The Latest From Omniverse

1. Blogs
2. Sessions
3. Training
4. Videos

### Omniverse News

[See All Tech Blogs](https://developer.nvidia.com/blog/tag/omniverse/)
[See All Topic News](https://blogs.nvidia.com/blog/tag/omniverse/)

Load More

[View All Sessions](https://www.nvidia.com/en-us/on-demand/playlist/playList-44408ff1-cbb9-4280-96eb-945d6451afa5/)

### OpenUSD Learning Path

Gain foundational knowledge, explore essential concepts, and harness the full potential of USD today with our Learn OpenUSD curriculum for developers and 3D practitioners.

[View Learning Path](https://www.nvidia.com/en-us/learn/learning-path/openusd.md)

### Digital Twin Learning Path

Learn the basics of building intelligent factories, warehouses, and industrial facilities with 3D integration, simulation, and real-time visualization for the era of physical AI.

[View Learning Path](https://www.nvidia.com/en-us/learn/learning-path/digital-twins.md)

### Robotics Learning Path

Explore core robotics concepts such as simulation, ROS, and AI training, and how they enable robots to navigate, adapt, and perform tasks in real-world environments.

[View Learning Path](https://www.nvidia.com/en-us/learn/learning-path/robotics.md)

[View All Videos](https://www.nvidia.com/en-us/on-demand/playlist/playList-da1f3d1c-6887-4952-9715-c48bf50e51f6/)

Next Steps

## Stay Up to Date on NVIDIA Omniverse News

Get the latest news, breakthroughs, and more sent straight to your inbox.

[Stay Informed](https://www.nvidia.com/en-us/omniverse/news.md)

## Frequently Asked Questions

### What is NVIDIA Omniverse?

NVIDIA Omniverse™ is a collection of libraries and microservices for developing physical AI applications such as industrial digital twins and robotics simulation. Leveraging NVIDIA’s deep expertise in accelerated computing and AI, Omniverse libraries enable software makers to integrate pre-built functionality into their solutions. These libraries include developer tools, GPU-accelerated libraries, and technologies packaged as microservices and cloud APIs for streamlined development and deployment.

### How can I build with NVIDIA Omniverse?

There are three ways to start developing with NVIDIA Omniverse libraries:

1. Use agent skills to make Omniverse capabilities callable as tools by physical AI simulation agents.
2. Use Omniverse libraries and microservices to integrate prebuilt physical AI simulation capabilities into applications and services.
3. Use NVIDIA Blueprints as reference workflows to jump-start physical AI applications, including industrial digital twins and robotics simulations.

Explore Omniverse libraries, agent skills, and NVIDIA Blueprints to get started [here](https://developer.nvidia.com/omniverse).

### How do agents use NVIDIA Omniverse?

Physical AI simulation agents can call NVIDIA Omniverse™ libraries, microservices, and APIs to enable scene data interoperability, scalable GPU-accelerated physics, physically based rendering, sensor simulation, and runtime workflows. These callable capabilities help agents generate, test, and refine simulation workflows.

### Where can I access legacy tools like Omniverse Launcher?

**NVIDIA Omniverse Launcher (Deprecated)**

The Omniverse Launcher was deprecated on October 1, 2025 to better align with developers and their expected development workflows.

Many of the Omniverse applications, tools, and assets that used to live in Launcher will transition to the following locations:

* Kit, Apps, Samples, Tools, and Templates are available on [GitHub](https://github.com/NVIDIA-Omniverse) and the [NGC Catalog](https://catalog.ngc.nvidia.com/collections?filters=platform%7COmniverse%7Cpltfm_omniverse&orderBy=weightPopularDESC&query=&page=&pageSize=).
* Connectors are available in the [NGC Catalog](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/omniverse/collections/omni_connectors).
* Extensions are available directly from the associated vendor's web pages or [NVIDIA OpenUSD Ecosystem Catalog](https://www.nvidia.com/en-us/accelerated-applications/usd-ecosystem.md).
* Content and Assets are available on [NVIDIA Documentation Hub (OmniDocs)](https://docs.omniverse.nvidia.com/).

Visit [Omniverse legacy tools](http://developer.nvidia.com/omniverse/legacy-tools) and [NVIDIA developer forums](https://forums.developer.nvidia.com/c/omniverse/platform/launcher/401) for more details.

**Nucleus Workstation**  
 Nucleus Workstation on Launcher was deprecated on October 1, 2025. Developers wishing to continue using Nucleus can obtain the Enterprise Nucleus Server software from the NGC Catalog (login required). The Enterprise Nucleus Server is free for testing and development, but an enterprise license is required for production use and includes enterprise support. See [Omniverse legacy tools](http://developer.nvidia.com/omniverse/legacy-tools) for more details.

### What is NVIDIA Cosmos, and how is it different from Omniverse?

[NVIDIA Cosmos](https://www.nvidia.com/en-us/ai/cosmos.md) is a [world model (WFM)](https://www.nvidia.com/en-us/glossary/world-models.md) development platform. At its core are Cosmos WFMs that generate world states as videos using multimodal input.

Developers can input Omniverse simulations as instructional videos to [the Cosmos Transfer WFM](https://github.com/nvidia-cosmos/cosmos-transfer2.5) model to generate controllable, photorealistic synthetic data.

Together, Omniverse provides the simulation environment before and after training, while Cosmos photoreal controllable synthetic data to train physical AI models.