AI Agent Skills

Run agents like Hermes and OpenClaw more securely inside NVIDIA OpenShell with managed inference

Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks.

AI agent skills published by NVIDIA

Read and write large cuPyNumeric arrays to HDF5 with Legate's parallel, distributed HDF5 I/O (legate.io.hdf5: to_file, from_file, from_file_batched). Use when a

Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether…

DALI imperative dynamic mode (`nvidia.dali.experimental.dynamic`, ndd): use when working on ndd code or migrating pipelines; skip pipeline-only tasks.

Run end-to-end calibration on the shipped sample dataset (sdg_08_2_sample_data_010926.zip) against a running AMC microservice. Use when user says 'test sample dataset',…

GPU-accelerated terminal board that puts all your sessions on an infinite canvas

rapids-singlecell: GPU-accelerated framework for scRNA analysis

⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.

AI 基础知识 - GPU 架构、CUDA 编程、大模型基础及AI Agent 相关知识。

Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results. Use when use…

GPU-accelerated micromagnetic simulator

See your agent think. Real-time observability for 12 AI agent runtimes - OpenClaw, NVIDIA NemoClaw, Claude Code, Codex & 8 more.