
Guides an agent through diagnosing NVSHMEM runtime failures and drafting bug reports
- Open source
- 4K GitHub stars
- Developer tools

Guides an agent through diagnosing NVSHMEM runtime failures and drafting bug reports

Routes NVSHMEM performance requests to the right specialist skill for data, transport, NIC

Orchestrates CAD and source assets into SimReady USD with material, physics and validation

Routes agents through building USD viewer apps with OVRTX rendering, XR, GPU and stylized

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

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

Orchestrates video data augmentation and auto-labeling runs on the OSMO platform

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

Guides integrating PhysicsNeMo ShardTensor domain parallelism into multi-GPU training

Builds and backtests stock portfolios with Mean-CVaR and variance-cap optimization

Diagnoses and narrowly repairs one reproduced NVIDIA PVA operator failure

Checks whether a host and Jetson board are ready for NVIDIA PVA development work

Generates, changes, or repairs vectorized NVIDIA PVA operators from a validated spec

Installs and configures the NVIDIA PVA SDK, NVVPU compiler and L4T board runtime

Writes a validated NVIDIA PVA operator spec, test matrix and OpGen handoff

Deploys, configures, troubleshoots and tears down the NVIDIA RAG Blueprint stack

Benchmarks a deployed NVIDIA RAG server for latency, throughput and citation quality

Guides swapping the DeepStream detector in VSS Alerts verification mode to a custom ONNX

Guides swapping the VLM behind NVIDIA's VSS Alerts Blueprint and verifying the change

Lets your agent open, edit and save RTX Remix mod projects through the Toolkit's MCP

Diagnoses why a Run:ai workload failed, crashed or stopped, with cited evidence

Drafts a governance skill card for an existing agent skill directory

Finds the weakest VCN classify predictions and ranks them for augmentation via TAO

Validates TAO job artifacts: spec bundles, job records, results layout and best_rec

Converts NVIDIA TAO DAFT datasets between supported formats via the tao-daft CLI

Moves TAO job data to and from compute containers, choosing the storage tier first

Gates TAO model launches behind preflight checks, image confirmation and a review step

Mines unique source images closest to target samples for object detection datasets

Routes weak VCN samples into per-module parquet subsets for mining and AnomalyGen

Runs an iterative NVIDIA TAO AOI loop that improves PCB defect-inspection models