-
NVIDIA
- Seattle, WA
- @katieelink
Stars
AI agents running research on single-GPU nanochat training automatically
RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.
Cognitive Architectures for Multi-Agent Teams
Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas
An extremely fast Python package and project manager, written in Rust.
AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
[WIP] Resources for AI engineers. Also contains supporting materials for the book AI Engineering (Chip Huyen, 2025)
Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.
Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks
Tools to scrape publications & their metadata from pubmed, arxiv, medrxiv, biorxiv and chemrxiv.
RadBench is a radiology benchmark framework developed by Harrison.ai.
High accuracy RAG for answering questions from scientific documents with citations
Open source implementation of AlphaFold3
Medplum is a healthcare platform that helps you quickly develop high-quality compliant applications.
A private and secure generative AI tool, based on GPT and o models, deployed for non-clinical use at Dana-Farber Cancer Institute
Minimal sharded dataset loaders, decoders, and utils for multi-modal document, image, and text datasets.
A package of clinically validated score calculations designed for easy integration into proprietary software systems.
A collection of learning resources for curious software engineers
In-Context Learning for eXtreme Multi-Label Classification (XMC) using only a handful of examples.
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.
On-device Speech AI for Apple Silicon