# Develop Lightweight USD Runtimes Faster with AI Agents

DevFeed: [Develop Lightweight USD Runtimes Faster with AI Agents](<https://devfeed.tech/articles/develop-lightweight-usd-runtimes-faster-with-ai-agents-6805.md>)

Original publisher: [Read original article](<https://developer.nvidia.com/blog/develop-lightweight-usd-runtimes-faster-with-ai-agents/>)

Author: Michelle Horton

Published: 2026-07-15T21:57:23Z

Content type: article

Language: en

Sources: [NVIDIA Developer](<https://devfeed.tech/sources/nvidia-developer.md>), [NVIDIA Technical Blog](<https://devfeed.tech/sources/nvidia-technical-blog.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Simulation and Design](<https://devfeed.tech/topics/simulation-and-design.md>), [Code](<https://devfeed.tech/topics/code.md>), [Nvidia](<https://devfeed.tech/topics/nvidia.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [code](<https://devfeed.tech/tags/code.md>), [developer-tools-techniques](<https://devfeed.tech/tags/developer-tools-techniques.md>), [featured](<https://devfeed.tech/tags/featured.md>), [hackathon](<https://devfeed.tech/tags/hackathon.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [omniverse](<https://devfeed.tech/tags/omniverse.md>), [openusd](<https://devfeed.tech/tags/openusd.md>), [physical-ai](<https://devfeed.tech/tags/physical-ai.md>), [robotics](<https://devfeed.tech/tags/robotics.md>), [simulation-modeling-design](<https://devfeed.tech/tags/simulation-modeling-design.md>)

## AI overview

This article presents nanousd-labs, an experimental NVIDIA Omniverse Labs project that uses AI agents and the machine-readable USD Core Specification to generate lightweight, compliant OpenUSD runtimes. It explains how agents generate and validate code against specification-derived tests, enabling runtimes tailored to memory, performance, language, and deployment constraints.

## Source excerpt

OpenUSD is an open, extensible framework that provides a common scene description language for physical AI. It enables teams to bring CAD data, simulation...