Skip to content
@NVIDIA-NeMo

NVIDIA-NeMo

NVIDIA NeMo

Featured repositories · November 2026

🛡️ NeMo Safe Synthesizer: Create private, safe versions of sensitive tabular datasets.

Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility - enabling flexible model selection, benchmarking, and cost/performance optimization.

Research preview: skills that help your coding assistant build evaluations for custom agents, assess the quality of existing suites, and find behavior-coverage gaps. Works today with NeMo Gym and Harbor.

A scalable, agentic-first, and HuggingFace-native RL framework for research (9k lines).

Developer Asset Hub for NVIDIA Nemotron — A one-stop resource for training recipes, usage cookbooks, datasets, and full end-to-end reference examples to build with Nemotron models

Popular repositories Loading

  1. Speech Speech Public

    A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

    Python 18.7k 3.7k

  2. Guardrails Guardrails Public

    NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

    Python 7.4k 897

  3. Switchyard Switchyard Public

    Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility - enabling flexible model selection, benchmarking, and cost…

    Rust 3.5k 357

  4. DataDesigner DataDesigner Public

    🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.

    Python 2.4k 243

  5. labs-OO-Agents labs-OO-Agents Public

    NVIDIA Object Oriented Agents: the Pythonic way to build AI Agents.

    Python 2.3k 316

  6. Nemotron Nemotron Public

    Developer Asset Hub for NVIDIA Nemotron — A one-stop resource for training recipes, usage cookbooks, datasets, and full end-to-end reference examples to build with Nemotron models

    Jupyter Notebook 2.3k 473

Repositories

Showing 10 of 32 repositories
  • Megatron-Bridge Public

    Training library for Megatron-based models with bidirectional Hugging Face conversion capability

    NVIDIA-NeMo/Megatron-Bridge's past year of commit activity
    Python 985 Apache-2.0 577 270 (1 issue needs help) 245 Updated Nov 7, 2026
  • Gym Public

    Evaluate and improve models and agents using environments

    NVIDIA-NeMo/Gym's past year of commit activity
    Python 1,321 Apache-2.0 455 625 805 Updated Nov 7, 2026
  • RL Public

    Scalable toolkit for efficient model reinforcement

    NVIDIA-NeMo/RL's past year of commit activity
    Python 2,117 Apache-2.0 636 586 (3 issues need help) 802 Updated Nov 7, 2026
  • UserSim Public

    🎭 NeMo User Sim: Improve models and agents with population-grounded simulated users, even before production traffic exists.

    NVIDIA-NeMo/UserSim's past year of commit activity
    Python 35 Apache-2.0 1 5 14 Updated Nov 7, 2026
  • nemo-helix Public

    NeMo Helix: Make the agents you ship faster, more accurate, and safer.

    NVIDIA-NeMo/nemo-helix's past year of commit activity
    Python 137 Apache-2.0 49 23 140 Updated Nov 7, 2026
  • Automodel Public

    🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support

    NVIDIA-NeMo/Automodel's past year of commit activity
    Python 1,079 Apache-2.0 370 210 (6 issues need help) 295 Updated Nov 7, 2026
  • Guardrails Public

    NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

    NVIDIA-NeMo/Guardrails's past year of commit activity
    Python 7,445 897 160 (3 issues need help) 111 Updated Nov 7, 2026
  • Run Public

    A tool to configure, launch and manage your machine learning experiments.

    NVIDIA-NeMo/Run's past year of commit activity
    Python 264 Apache-2.0 119 20 29 Updated Nov 7, 2026
  • Switchyard Public

    Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility - enabling flexible model selection, benchmarking, and cost/performance optimization.

    NVIDIA-NeMo/Switchyard's past year of commit activity
    Rust 3,492 Apache-2.0 357 51 64 Updated Nov 7, 2026
  • .github Public
    NVIDIA-NeMo/.github's past year of commit activity
    Python 2 7 0 2 Updated Nov 6, 2026