Demos of what to do after "hello world" works with NemoClaw installer.

NVIDIA Kaggle Plugin gives agents end-to-end Kaggle competition workflows through a single skill, nvidia-kaggle-skill. It can gather competition context, study public writeups and notebooks, reprod…

🎁 7,400,000+ Unsplash images made available for research and machine learning

An agent harness that compiles a model into one provably-correct, self-retargeting CUDA megakernel and self-tunes it past cuBLAS at batch-1 LLM decode, paper: https://arxiv.org/abs/2606.09682

Spark RAPIDS MLlib – accelerate Apache Spark MLlib with GPUs

Paste a GitHub repo URL and see where your stargazers live on an interactive world map. Free, no login.

Turn any document or a whole zip into an interactive knowledge graph, using a self-hosted Qwen3.6-35B-A3B-MTP on a single NVIDIA L4

Concept Modeling: Topic Modeling on Images and Text

Collection of step-by-step playbooks for setting up AI/ML workloads on NVIDIA DGX Spark devices with Blackwell architecture.

Batched GPU augmentations for 3D medical images, replacing MONAI's per-sample transforms with fused Triton kernels

Hyperbolic Safety-Aware Vision-Language Models. CVPR 2025

A platform for reproducible world model research and evaluation

Cosmos-H-Surgical

NVARC solution to ARC-AGI-2

NeMo Retriever Library is a scalable, performance-oriented document content and metadata extraction microservice. NeMo Retriever Library uses specialized NVIDIA NIM microservices to find, contextua…

RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing …

A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downs…

Official code for "HMP-Net: A Hierarchical Multi-Prior Network for Brain Tumor Segmentation Integrating Physics, Topology, and Tumor Dynamics"

cuVS - a library for vector search and clustering on the GPU

Agent Skills for Rust, Python, and TypeScript — enforce language lint rules while writing code. Open Agent Skills format (agentskills.io).

A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/

A project showcasing how to leverage AI coding assistants (Cursor, Claude Code, etc.) for accelerated NVIDIA DeepStream SDK application development using a curated agentic skill and structured prom…

Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.

GPU accelerated decision optimization

NVIDIA cuOpt examples for decision optimization

Open-source AI job search: scan job portals, evaluate listings with a structured A-F rubric into a 1.0-5.0 score, tailor your CV, track applications — runs locally in your AI coding CLI (Claude Cod…

Google Drive for AI agents. Store any file and search by meaning across modalities.