Open source. Open possibilities.

einops is a flexible tensor operations library using Einstein-like notation for readable, reliable code across PyTorch, JAX, TensorFlow, NumPy and more.

AutoKeras is an open-source AutoML library built on Keras that automates deep learning model search for image, text, and structured data tasks.

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.

Cog packages machine learning models into production-ready Docker containers, automatically handling CUDA compatibility and generating an HTTP inference API from Python type definitions.

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.

Frigate is a local NVR for IP cameras with realtime AI object detection, built for Home Assistant. It uses OpenCV and TensorFlow, motion-triggered detection, MQTT, object-based retention, 24/7 recording, RTSP restreaming and low-latency WebRTC/MSE live view.

Spleeter is a Python-based music source separation library by Deezer Research that uses pretrained TensorFlow models to split audio into stems like vocals, drums, bass, and more.

TensorFlow is an end-to-end open source platform for machine learning, providing a flexible ecosystem of tools and libraries for building and deploying ML-powered applications.