--- title: Develop Lightweight USD Runtimes Faster with AI Agents description: nanousd-labs is an NVIDIA Omniverse Labs project that uses AI agents to generate lightweight USD runtimes directly from the USD Core Specification rather than... canonical: https://daily.dev/posts/develop-lightweight-usd-runtimes-faster-with-ai-agents-e8v0igi2o twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Develop Lightweight USD Runtimes Faster with AI Agents | daily.dev og:description: nanousd-labs is an NVIDIA Omniverse Labs project that uses AI agents to generate lightweight USD runtimes directly from the USD Core Specification rather than... og:url: https://daily.dev/posts/develop-lightweight-usd-runtimes-faster-with-ai-agents-e8v0igi2o og:image: https://api.daily.dev/og/posts/e8v0IGi2O.png og:image:alt: Develop Lightweight USD Runtimes Faster with AI Agents og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Develop Lightweight USD Runtimes Faster with AI Agents **[NVIDIA Developer](https://daily.dev/sources/nvidiadev)** · 9 min read · 0 upvotes · 0 comments ## Summary nanousd-labs is an NVIDIA Omniverse Labs project that uses AI agents to generate lightweight USD runtimes directly from the USD Core Specification rather than adapting large existing codebases. The methodology treats the formal, machine-readable USD Core Specification as a contract: agents read it section by section, generate compliant C++/C ABI code, and validate output against a spec-derived test suite. The result is a minimal, purpose-built USD data layer (no renderer) with a stable C API callable from any language, including a Python package. Two entry points are provided: cloning and building nanousd directly, or following a 10-minute tutorial to understand the skill-graph methodology for generating a USDA parser. Engineers retain ownership of architecture and performance decisions while agents handle mechanical spec-to-code work like parsing and scene composition. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [NVIDIA OpenUSD Meets Cloud HPC: Part 1](https://daily.dev/posts/nvidia-openusd-meets-cloud-hpc-part-1-klsopwolx) · Medium · 0 upvotes · 0 comments - [Building an Interactive AI Agent for Lightning-Fast Machine Learning Tasks](https://daily.dev/posts/building-an-interactive-ai-agent-for-lightning-fast-machine-learning-tasks-58tcuc9h8) · NVIDIA Developer · 0 upvotes · 0 comments - [AOUSD Published OpenUSD Core Specification 1.0](https://daily.dev/posts/aousd-published-openusd-core-specification-1-0-lbuvmgbqy) · 80 LEVEL · 0 upvotes · 0 comments - [Into the Omniverse: OpenUSD and NVIDIA Halos Accelerate Safety for Robotaxis, Physical AI Systems](https://daily.dev/posts/into-the-omniverse-openusd-and-nvidia-halos-accelerate-safety-for-robotaxis-physical-ai-systems-6nhnxgnxg) · NVIDIA · 0 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#nvidia](https://daily.dev/tags/nvidia), [#openusd](https://daily.dev/tags/openusd) [View this post on daily.dev](https://daily.dev/posts/develop-lightweight-usd-runtimes-faster-with-ai-agents-e8v0igi2o) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Develop Lightweight USD Runtimes Faster with AI Agents","url":"https://daily.dev/posts/develop-lightweight-usd-runtimes-faster-with-ai-agents-e8v0igi2o","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/develop-lightweight-usd-runtimes-faster-with-ai-agents-e8v0igi2o"},"datePublished":"2026-07-15T22:00:19.369Z","dateModified":"2026-07-15T22:00:42.638Z","description":"nanousd-labs is an NVIDIA Omniverse Labs project that uses AI agents to generate lightweight USD runtimes directly from the USD Core Specification rather than...","image":"https://media.daily.dev/image/upload/s--0_ODbtD2--/f_auto/v1722860399/public/Placeholder%2008","thumbnailUrl":"https://media.daily.dev/image/upload/s--0_ODbtD2--/f_auto/v1722860399/public/Placeholder%2008","isAccessibleForFree":true,"articleSection":"NVIDIA Developer","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"NVIDIA Developer","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/86e45aab42ba48ce83103d01b1119910","url":"https://daily.dev/sources/nvidiadev"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/develop-lightweight-usd-runtimes-faster-with-ai-agents-e8v0igi2o","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,nvidia,openusd","timeRequired":"PT9M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"NVIDIA Developer","item":"https://daily.dev/sources/nvidiadev"},{"@type":"ListItem","position":3,"name":"Develop Lightweight USD Runtimes Faster with AI Agents"}]} ```