Find trending repositories by name or description.
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.
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)
Training library for Megatron-based models with bidirectional Hugging Face conversion capability
A set of extensions for Nemo
NEMO is a laboratory logistics web application. Use it to schedule reservations, control tool access, track maintenance issues, and more.
A set of actions for extending the functionality of the GNOME Files (Nautilus), Nemo, Caja, Dolphin, Thunar and PCManFM-Qt file managers.
NeMo text processing for ASR and TTS
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
A project to improve skills of large language models
An Operator for deployment and maintenance of NVIDIA NIMs and NeMo microservices in a Kubernetes environment.
NeMo Retriever Library is a scalable, performance-oriented document content and metadata extraction microservice. NeMo Retriever Library uses specialized NVIDIA NIM microservices to find, contextualize, and extract text, tables, charts and images that you can use in downstream generative applications.
The NVIDIA NeMo Agent toolkit is an open-source library for efficiently connecting and optimizing teams of AI agents.
Scalable toolkit for efficient model reinforcement
🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support
Evaluate and improve models and agents using environments
Agentic RL on Any Harness at Scale
Multi-language agent runtime and library for execution scope management, lifecycle events, and middleware on tool and LLM calls.
An agentic-first RL framework for research (9k lines).
NeMo-Speech.cpp is a lightweight C++ inference runtime for Speech models
NVIDIA Object Oriented Agents: the Pythonic way to build AI Agents.