Hardware
Develop Lightweight USD Runtimes Faster with AI Agents
nanousd‑labs, part of NVIDIA Omniverse Labs, uses AI agents to generate lightweight, spec‑compliant USD runtimes directly from the USD Core Specification, sidestepping the need to adapt large legacy c
nanousd‑labs, part of NVIDIA Omniverse Labs, uses AI agents to generate lightweight, spec‑compliant USD runtimes directly from the USD Core Specification, sidestepping the need to adapt large legacy codebases and allowing customized memory, performance, and ABI constraints. The agents treat the USD Core Specification as a formal contract, implement it automatically, and validate compliance with specification‑derived test suites, producing a stable C ABI runtime that integrates seamlessly with existing OpenUSD stacks and supports dynamic backend swapping. The project welcomes community contributions and extensions, aligning with the Alliance for OpenUSD’s Core Spec Working Group to maintain an open, extensible framework for shared, physically accurate scene descriptions.
Related
Source: NVIDIA Developer | 2026-07-15