BREAKING
NVIDIA agents turn USD spec into runtimes
Spec-first, agent-assisted workflow
1
USD Core Spec
↓
2
Port codebase
↓
3
AI agents generate
↓
4
Conformant runtime
Built for physical AI
Old approach
Legacy
●
Port or trim OpenUSD
●
Laborious and error-prone
●
One-size-fits-all stack
nanousd-labs
New
●
Generate from spec
●
Custom runtimes
●
Tuned for physical AI
Dual Apache 2.0 and CC-BY-4.0
nanousd: portable C-ABI core
1
nanousd C-ABI
↓
2
nanousd-python
↓
3
nanousdview
↓
4
Vulkan/GL/Metal
A proof of concept, not a product
AI NEWS BLITZ
NVIDIA's Omniverse Labs shows AI agents building 3D scene runtimes straight from spec.