Open source. Open possibilities.

PaddlePaddle is an industrial-grade deep learning platform providing a comprehensive framework for machine learning, including model libraries and development kits.

PyTorch is an open-source machine learning library providing tensor computation with GPU acceleration and a flexible deep neural network framework based on a tape-based autograd system.

Keras 3 is a multi-backend deep learning framework that allows users to build and train models using JAX, TensorFlow, PyTorch, or OpenVINO.

A comprehensive toolkit for computer vision that provides model-agnostic building blocks for data loading, visualization, and dataset management.

A tiny GPT language model (~540M parameters) designed to be trained from scratch on consumer laptop hardware, with pretraining on Fineweb-edu and chat finetuning capabilities.

Gradio is an open-source Python library for quickly building and sharing web applications for machine learning models, APIs, or any Python function without requiring web development experience.

Magika is Google's AI-powered file content type detection tool. It uses a small deep learning model to identify 200+ file types in milliseconds on a single CPU, with ~99% accuracy. Available as a Rust CLI plus Python, JavaScript and Go bindings.

Pyro is a flexible, scalable deep probabilistic programming library built on PyTorch, supporting universal probabilistic models and automated inference.

Free, open-source AI engineering curriculum from first principles: 523 lessons in 20 phases (~342 hours), with math-to-production coverage in Python, TypeScript, Rust, and Julia. Every lesson ships a reusable prompt, skill, agent, or MCP server; includes an installable AI tutor and Claude certification prep.

Sonnet is a neural network library by DeepMind built on TensorFlow 2. It provides simple, composable abstractions via the snt.Module concept for machine learning research, supporting custom modules, serialization, and distributed training.

YuE2 is an open music generation model that unifies symbolic planning with audio synthesis: it turns lyrics and a style prompt into an editable melody-and-chord score, then renders a full song with vocals and accompaniment. It also supports zero-shot covers and agentic score editing.

A curated collection of 107 foundational generative AI research papers with comprehensive summaries, learning roadmaps, glossaries, and decision guides—making cutting-edge AI research accessible to everyone.

A comprehensive web interface for Stable Diffusion implemented using the Gradio library, providing a wide array of tools for AI image generation and manipulation.

A growing collection of 61 computer vision tutorials covering state-of-the-art models like YOLO11, SAM 3, RF-DETR, and Qwen3-VL for object detection, segmentation, OCR, and more.

Tesseract.js is a JavaScript OCR library that extracts text from images in over 100 languages. It runs in browsers via WebAssembly and on Node.js, wrapping the Tesseract engine without modifying its recognition model.

A curated collection of pre-trained, state-of-the-art machine learning models in the ONNX format, spanning computer vision, NLP, generative AI, and graph machine learning. The repository is being deprecated with models migrating to Hugging Face.

A modern C++ toolkit providing machine learning algorithms and tools for data analysis and real-world application development.

EasyOCR is a ready-to-use optical character recognition library supporting 80+ languages and major writing scripts. It offers a simple Python API and CLI, with PyTorch-based detection and recognition models, plus options for custom training.

A collection of machine learning and deep learning code examples and tutorials accompanying online courses. Covers topics from linear regression to reinforcement learning, NLP, computer vision, and generative AI.

Label Studio is an open-source, multi-type data labeling tool supporting audio, text, images, video, and time series with a simple UI and export to various model formats.