NVIDIA-NeMo
Open-source projects on GitHub: Speech, Guardrails and Switchyard
Consolidated Product Portfolio
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)
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.
🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
Scalable data pre processing and curation toolkit for LLMs
NVIDIA Object Oriented Agents: the Pythonic way to build AI Agents.
🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support
An agentic-first RL framework for research (9k lines).
A project to improve skills of large language models
Evaluate and improve models and agents using environments
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
Company Profile & Strategy
NVIDIA-NeMo maintains 10 open-source projects on GitHub, including Speech, Guardrails and Switchyard. Primary language: Python.
Open-Source Footprint
Save & manage the vendor's products in Productapp.
Save and manage this vendor's products in Productapp.