NVIDIA-NeMo

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)

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

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

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

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

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

Scalable toolkit for efficient model reinforcement

Scalable data pre processing and curation toolkit for LLMs

Evaluate and improve models and agents using environments

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

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

A project to improve skills of large language models

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

Agentic RL on Any Harness at Scale

Open-source library for scalable, reproducible evaluation of AI models and benchmarks.

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

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

🕵️ NeMo Anonymizer: Detect and protect PII through context-aware replacement and rewriting

State-of-the-art framework for fast, large-scale training and inference of diffusion models