Skip to content
@NVIDIA

NVIDIA Corporation

Pinned Loading

  1. cosmos cosmos Public

    NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.

    Jupyter Notebook 12.1k 918

  2. NemoClaw NemoClaw Public

    Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference

    TypeScript 22.8k 3.1k

  3. TensorRT-LLM TensorRT-LLM Public

    TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…

    Python 14.9k 2.8k

  4. cutlass cutlass Public

    CUDA Templates and Python DSLs for High-Performance Linear Algebra

    C++ 10.6k 2.1k

  5. warp warp Public

    A Python framework for GPU-accelerated simulation, robotics, and machine learning.

    Python 7.2k 661

  6. open-gpu-kernel-modules open-gpu-kernel-modules Public

    NVIDIA Linux open GPU kernel module source

    C 17.5k 1.9k

Repositories

Showing 10 of 821 repositories
  • aicr Public

    Tooling for optimized, validated, and reproducible GPU-accelerated AI runtime in Kubernetes

    NVIDIA/aicr's past year of commit activity
    Go 442 Apache-2.0 117 141 (1 issue needs help) 13 Updated Oct 19, 2026
  • numba-cuda-mlir Public

    repo for Numba-CUDA-MLIR

    NVIDIA/numba-cuda-mlir's past year of commit activity
    Python 73 Apache-2.0 36 30 34 Updated Oct 19, 2026
  • cuopt Public

    GPU accelerated decision optimization

    NVIDIA/cuopt's past year of commit activity
    Cuda 1,066 Apache-2.0 245 187 60 Updated Oct 19, 2026
  • cudf Public

    cuDF - GPU DataFrame Library

    NVIDIA/cudf's past year of commit activity
    C++ 9,780 Apache-2.0 1,132 1,187 (30 issues need help) 241 Updated Oct 19, 2026
  • OSMO Public

    The developer-first platform for scaling complex Physical AI workloads across heterogeneous compute—unifying training GPUs, simulation clusters, and edge devices in a simple YAML

    NVIDIA/OSMO's past year of commit activity
    Python 271 Apache-2.0 61 53 42 Updated Oct 19, 2026
  • OpenShell Public

    OpenShell is the safe, private runtime for autonomous AI agents.

    NVIDIA/OpenShell's past year of commit activity
    Rust 16,707 Apache-2.0 1,815 368 (2 issues need help) 184 Updated Oct 19, 2026
  • AI-Factory-Operations-Agent Public

    Deploy AI agents to investigate cluster issues and streamline governed AI factory operations.

    NVIDIA/AI-Factory-Operations-Agent's past year of commit activity
    TypeScript 25 Apache-2.0 3 1 3 Updated Oct 19, 2026
  • Model-Optimizer Public

    A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.

    NVIDIA/Model-Optimizer's past year of commit activity
    Python 5,370 Apache-2.0 756 104 393 Updated Oct 19, 2026
  • MatX Public

    An efficient C++20 GPU numerical computing library with Python-like syntax

    NVIDIA/MatX's past year of commit activity
    C++ 1,449 BSD-3-Clause 130 11 10 Updated Oct 19, 2026
  • NeMo-Relay Public

    Multi-language agent runtime and library for execution scope management, lifecycle events, and middleware on tool and LLM calls.

    NVIDIA/NeMo-Relay's past year of commit activity
    Rust 200 Apache-2.0 86 2 13 Updated Oct 19, 2026