NVIDIA Corporation
Organization@nvidia
84
Published Tools
84,978
Total Stars
131,872
Weekly Downloads
31,902
GitHub Followers
830
Public Repos
100/100
Avg Security
Published Tools
3 MCP Servers43 Skills38 Agentsacross 9 categoriesGenerative AI framework built for researchers and PyTorch developers working on Large Language Models (LLMs), Multimodal Models (MMs), Automatic Speech Recognition (ASR), Text to Speech (TTS), and Computer Vision (CV) domains.
...moreOngoing research training transformer models at scale.
nv052193, Mads Kongsbak, Tianhao Li, Phyllis Poh, Razvan Dinu, Zander Mackie, Greg Stephens, Ahsan Ayub, Jonathan Liberman, Gustav Fredrikson, Oh Tien Cheng, Brain John, Naman Mishra, Soumili Nandi, Arjun Krishna, Mihailo Milenkovic, Kai Greshake, Martin Borup-Larsen, Emmanuel Ferdman, Eric Therond, Zoe Nolan, Harsh Raj, Shine-afk, Rafael Sandroni, Eric Hacker, Blessed Uyo, Ikko Eltociear Ashimine, iamnotcj, Dwight Temple, Shane Rosse, Masaya Ogushi, Viktor T. Zetterberg, Erwan Roussel, Matthew Rowe, Aishwarya Padmakumar, Marco Rosa, Ian Chu, Mike McKiernan, Divya Chitimalla, Katherine Luna, Dave Baker, Jack Kelly, Amrit Prakash, Cássia Sampaio, Nakul Rajpal, Noah Oeksuez, Dhruv Malik, Patricia Pampanelli, Joseph Davis Chamdani, Rob Geada, Ashish RajAnand, Paulina Kalicka, Gal Moshkovitz, Jack Smith, Paul A. Parkanzky, Leif Hancox-Li, Fabrizio Rocco, Sai Chandra Pandraju, Harish Kolla, Snehal Vartak, Abhiraj Sinha, Harsh Motla, Otavio Padovani, Siddhant Mishra, dyrtyData, Leone Lage Perdigão, Lucas Wang
LLM vulnerability scanner
NVIDIA
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
nv052193, Mads Kongsbak, Tianhao Li, Phyllis Poh, Razvan Dinu, Zander Mackie, Greg Stephens, Ahsan Ayub, Jonathan Liberman, Gustav Fredrikson, Oh Tien Cheng, Brain John, Naman Mishra, Soumili Nandi, Arjun Krishna, Mihailo Milenkovic, Kai Greshake, Martin Borup-Larsen, Emmanuel Ferdman, Eric Therond, Zoe Nolan, Harsh Raj, Shine-afk, Rafael Sandroni, Eric Hacker, Blessed Uyo, Ikko Eltociear Ashimine, iamnotcj, Dwight Temple, Shane Rosse, Masaya Ogushi, Viktor T. Zetterberg, Erwan Roussel, Matthew Rowe, Aishwarya Padmakumar, Marco Rosa, Ian Chu
garak (LLM vulnerability scanner) - packaged by NVIDIA Eval Factory
NVIDIA Framework for LLM Inference(Transitioned to TensorRT-LLM)
A library for accelerating Transformer model training on NVIDIA GPUs.
NVIDIA Corporation
Professional domain benchmark for evaluating LLMs on Physics PhD, Chemistry PhD, Finance MBA, and Consulting MBA tasks
NVIDIA Corporation
Subpackage for RagaAI Catalyst integration in NeMo Agent Toolkit
NVIDIA Multi-Storage Client Team
Unified high-performance Python client for object and file stores.
NVIDIA Corporation
LangChain Deep Agents adapter for NeMo Fabric
GitHub Actions
Form control utilities and validation providing mixins, validators, and schema-based validation. Includes form association, event handling, and support for complex data types.
...moreGitHub Actions
Core CSS foundation for the NVIDIA Elements design system, providing layout utilities, typography styles, and view transitions.
...moreGitHub Actions
Themes for the Elements design system, providing comprehensive color palettes, typography, and spacing.
GitHub Actions
Provides integration with VS Code's Monaco editor for code editing, syntax highlighting, and diff visualization.
GitHub Actions
Lint configurations and custom rules for NVIDIA Elements projects, providing Elements-specific HTML and CSS validations.
GitHub Actions
The UI SDK and agent-ready developer toolkit for AI factories, robotics, and autonomous vehicles. Provides a set of accessible and themeable UI components.
...moreNVIDIA Corporation
Nvidia Model Optimizer: A unified library of SOTA model optimization techniques like quantization, pruning, Neural Architecture Search (NAS), distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.
...moreNVIDIA Corporation
numba-cuda-mlir Python Compiler (CuBIE patched build)
Air Team
Python SDK for creating, running and managing simulations on NVIDIA Air
NVIDIA CORPORATION & AFFILIATES
Launch ephemeral agents for single tasks in OpenShell sandboxes.
SkillSpector: Security scanner for AI agent skills (Claude Code, Cursor, and similar). Scans skills for vulnerabilities, malicious patterns, and security risks before installation. Supports Git repos, URLs, zips, and local directories; runs static pattern checks and optional LLM semantic analysis; outputs terminal, JSON, and Markdown reports with risk scoring.
...moreNVIDIA
Providing reproducibility in deep learning frameworks
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer Mixture-of-Experts architecture with multi-token prediction (MTP), it delivers over 50% higher token generation compared to leading open models. The model features a 1M token context window for long-term agent coherence, cross-document reasoning, and multi-step task planning. Latent
...moreNVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully open with open-weights, datasets and recipes so developers can easily customize, optimize, and deploy the model on their infrastructure for maximum privacy and security.
...moreNVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully open with open-weights, datasets and recipes so developers can easily customize, optimize, and deploy the model on their infrastructure for maximum privacy and security.
...moreNVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy with Mamba’s memory-efficient sequence modeling for significantly higher throughput and lower latency. The model supports inputs of text and multi-image documents, producing natural-language outputs. It is trained on high-quality NVIDIA-curated synthetic datasets
...moreNVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy with Mamba’s memory-efficient sequence modeling for significantly higher throughput and lower latency. The model supports inputs of text and multi-image documents, producing natural-language outputs. It is trained on high-quality NVIDIA-curated synthetic datasets
...moreLlama-3.3-Nemotron-Super-49B-v1.5 is a 49B-parameter, English-centric reasoning/chat model derived from Meta’s Llama-3.3-70B-Instruct with a 128K context. It’s post-trained for agentic workflows (RAG, tool calling) via SFT across math, code, science, and multi-turn chat, followed by multiple RL stages; Reward-aware Preference Optimization (RPO) for alignment, RL with Verifiable Rewards (RLVR) for step-wise reasoning, and iterative DPO to refine tool-use behavior. A distillation-driven Neural Arc
...moreNVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding with a final response. The model's reasoning capabilities can be controlled via a system prompt. If the user prefers the model to provide its final answer without intermediate reasoning traces, it can be configured to do so.
...moreNVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding with a final response. The model's reasoning capabilities can be controlled via a system prompt. If the user prefers the model to provide its final answer without intermediate reasoning traces, it can be configured to do so.
...moreNVIDIA's Llama 3.1 Nemotron 70B is a language model designed for generating precise and useful responses. Leveraging [Llama 3.1 70B](/models/meta-llama/llama-3.1-70b-instruct) architecture and Reinforcement Learning from Human Feedback (RLHF), it excels in automatic alignment benchmarks. This model is tailored for applications requiring high accuracy in helpfulness and response generation, suitable for diverse user queries across multiple domains. Usage of this model is subject to [Meta's Accep
...moreNVIDIA Corporation
Subpackage for RAGAS evaluators in NVIDIA NeMo Agent Toolkit
NVIDIA Corporation
Subpackage for FastMCP server integration in NeMo Agent Toolkit
NVIDIA Corporation
Subpackage for CrewAI integration in NeMo Agent Toolkit
NVIDIA Corporation
Subpackage for LangChain/LangGraph integration in NeMo Agent Toolkit
NVIDIA Corporation
Subpackage for MCP client integration in NeMo Agent Toolkit
nvidia
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer Mixture-of-Experts architecture with multi-token prediction (MTP), it delivers over 50% higher token generation compared to leading open models. The model features a 1M token context window for long-term agent coherence, cross-document reasoning, and multi-step task planning. Latent
...moreLlama-3.1-Nemotron-Ultra-253B-v1 is a large language model (LLM) optimized for advanced reasoning, human-interactive chat, retrieval-augmented generation (RAG), and tool-calling tasks. Derived from Meta’s Llama-3.1-405B-Instruct, it has been significantly customized using Neural Architecture Search (NAS), resulting in enhanced efficiency, reduced memory usage, and improved inference latency. The model supports a context length of up to 128K tokens and can operate efficiently on an 8x NVIDIA H100
...moreNVIDIA Corporation
pylibwholegraph - GPU Graph Storage for GNN feature and graph structure
NVIDIA Corporation
pylibwholegraph - GPU Graph Storage for GNN feature and graph structure
NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...
...more"NVIDIA Inc." <[email protected]>
AIPerf is a package for performance testing of AI models
NVIDIA Corporation
Python Bindings for the NVIDIA Management Library
NVIDIA
NeMo Evaluator — benchmark environments, pluggable solvers, interceptor proxy, and decision-grade scoring for LLMs
NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...
...moreNVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
...morenvidia
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
...moreNVIDIA Corporation
Typed, composable LLM routing with request/response translation and multi-backend orchestration
NVIDIA Kitmaker Team
Zero version placeholder for nemo_fabric_adapters_claude
NVIDIA CORPORATION & AFFILIATES
A simple Ray + vLLM + FSDP2 (AutoTP/EP/CP) stack for SFT and RL.
"NVIDIA Inc." <[email protected]>
Triton Model Analyzer is a tool to profile and analyze the runtime performance of one or more models on the Triton Inference Server
...moreNVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
...moreNVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...
...moreNVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...
...moreNVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...
...more"NVIDIA Inc." <[email protected]>
aiconfigurator: automatic disaggregated serving offline configuration
"NVIDIA Inc." <[email protected]>
Standalone core modeling, data, and Rust estimators for AIConfigurator
NVIDIA Kitmaker Team
Zero version placeholder for holoscan_inference_cu13
NVIDIA Kitmaker Team
Zero version placeholder for holoscan_inference
"NVIDIA Inc." <[email protected]>
AISimulate: GPU-free inference simulation and deployment configuration
nvidia
Switchyard is an open-source model router that switches between multiple models to optimize the cost of requests. By default it will use OpenRouter market data to select the most popular...
...moreSimReady AI Factory (AIF) tier: AIF core metadata, connection points (v0.1.0 geometry + v0.2.0 property vocabulary, coexisting), thermal cooling, and electrical capabilities/features, and the aif-entity profile
...more"NVIDIA Inc." <[email protected]>
AIPerf is a package for performance testing of AI models
"NVIDIA Inc." <[email protected]>
SemiAnalysis AgentX inference benchmark harness, built on AIPerf
NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...
...moreNVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...
...moreNVIDIA
Namespace protection for an internal NVIDIA BCM Python distribution
NVIDIA
Developer kit for working with the NVIDIA Physical AI Autonomous Vehicles Dataset