
Newton performance
SkillGuides measuring and speeding up a working Newton physics simulation without changing
- Open source
- 4K GitHub stars
- Developer tools


Guides measuring and speeding up a working Newton physics simulation without changing

Guides choosing a physics engine and Newton/ovnewton integration for Physical AI

Connects the Newton physics engine to an Omniverse ovstage for simulation and rendering

Routes users to the right PhysicsNeMo model, datapipe, or example for a physics ML task

Guides setup, GPU simulation targets, QPU access and @cudaq.kernel authoring in CUDA-Q

Helps agents find and recommend NVIDIA skills from the live catalog before general answers

Guides choosing, installing and verifying the NeMo Relay package for an agent or app

Plans and validates NVSHMEM and NVSHMEM4Py installs across packages, containers and source

Guides an agent through changing, refactoring or reviewing NVIDIA FastGen library code

Guides an agent through building, migrating and reviewing Microsoft Agent Framework code

Guides installing Earth2Studio with uv or pip, picking model extras, and setting env vars

Guides an agent through diagnosing NVSHMEM runtime failures and drafting bug reports
The closest alternatives to Newton usage are Newton performance, Physical AI physics selection, Using ovnewton, Physicsnemo discover and Cudaq guide.
Yes. Newton performance, Physical AI physics selection, Using ovnewton have a free or open-source option.