Skip to content
@NVIDIA-NeMo

NVIDIA-NeMo

Pinned Loading

  1. Curator Curator Public

    Scalable data pre processing and curation toolkit for LLMs

    Python 1.8k 361

  2. RL RL Public

    Scalable toolkit for efficient model reinforcement

    Python 2.1k 624

  3. Automodel Automodel Public

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

    Python 1.1k 352

  4. Megatron-Bridge Megatron-Bridge Public

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

    Python 974 568

  5. Guardrails Guardrails Public

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

    Python 7.4k 888

  6. Gym Gym Public

    Evaluate and improve models and agents using environments

    Python 1.3k 434

Repositories

Showing 10 of 32 repositories
  • 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 132 Apache-2.0 46 34 152 Updated Oct 31, 2026
  • Gym Public

    Evaluate and improve models and agents using environments

    NVIDIA-NeMo/Gym's past year of commit activity
    Python 1,307 Apache-2.0 434 604 727 Updated Oct 31, 2026
  • eval-author Public

    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.

    NVIDIA-NeMo/eval-author's past year of commit activity
    Python 10 Apache-2.0 1 6 17 Updated Oct 31, 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 33 Apache-2.0 1 2 16 Updated Oct 31, 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 3,467 Apache-2.0 347 51 53 Updated Oct 31, 2026
  • RL Public

    Scalable toolkit for efficient model reinforcement

    NVIDIA-NeMo/RL's past year of commit activity
    Python 2,095 Apache-2.0 624 580 (3 issues need help) 773 Updated Oct 31, 2026
  • 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 974 Apache-2.0 568 270 (1 issue needs help) 238 Updated Oct 31, 2026
  • labs-OO-Agents Public

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

    NVIDIA-NeMo/labs-OO-Agents's past year of commit activity
    Python 2,299 313 51 74 Updated Oct 31, 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 1,064 Apache-2.0 352 208 (7 issues need help) 288 Updated Oct 31, 2026
  • Curator Public

    Scalable data pre processing and curation toolkit for LLMs

    NVIDIA-NeMo/Curator's past year of commit activity
    Python 1,843 Apache-2.0 361 128 (10 issues need help) 159 Updated Oct 31, 2026
View all repositories