
Newton usage
SkillGuides an agent through setting up, building and debugging Newton physics simulations
- Open source
- 4K GitHub stars
- Developer tools


Guides an agent through setting up, building and debugging Newton physics simulations

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

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

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

Builds a minimal, vetted set of agent skills for a multi-step goal, with install checks

Designs AI agent architectures from requirements or audits existing agents for flaws

Picks Jetson-compatible containers and PyPI indexes for GPU ML on Orin and Thor

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

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

Runs Jetson encode, decode and transcode pipelines with checks on each stage's output

Guides an agent from a plain-text problem to an LP, MILP or QP formulation

Orchestrates video data augmentation and auto-labeling runs on the OSMO platform
The closest alternatives to Physical AI physics selection are Newton usage, Newton performance, Physicsnemo discover, Using ovnewton and Agent skill stack.
Yes. Newton usage, Newton performance, Physicsnemo discover have a free or open-source option.