DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

A toolkit for developing and comparing reinforcement learning algorithms.

Multi-agent framework, runtime and control plane. Built for speed, privacy, and scale.

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

Let us control diffusion models!

💫 Industrial-strength Natural Language Processing (NLP) in Python

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

You like pytorch? You like micrograd? You love tinygrad! ❤️

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

Code and documentation to train Stanford's Alpaca models, and generate the data.

DSPy: The framework for programming—not prompting—language models

Convert PDF to markdown + JSON quickly with high accuracy

The official Python library for the OpenAI API

The official Meta Llama 3 GitHub site

A modular graph-based Retrieval-Augmented Generation (RAG) system

Reverse engineered ChatGPT API

Open-Sora: Democratizing Efficient Video Production for All

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

A generative world for general-purpose robotics & embodied AI learning.

Generative Models by Stability AI

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

Fully open reproduction of DeepSeek-R1

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.