Examples and guides for using the Gemini API

JavaScript 3D library.

A collection of guides and examples for the Gemma open models from Google.

A collection of Three.js Shading Language (TSL) textures

Get started with building Fullstack Agents using Gemini 2.5 and LangGraph

Salesforce AI Research's open diffusion language model

A simple model of articulated human figure

LiteRT is the new name for TensorFlow Lite (TFLite). While the name is new, it's still the same trusted, high-performance runtime for on-device AI, now with an expanded vision.

Supporting PyTorch models with the Google AI Edge TFLite runtime.

A modern model graph visualizer and debugger

Official Code Release for [SIGGRAPH 2025] RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global Illumination

A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.

A web framework for building multi-user virtual reality experiences.

Documentation on the Hubs open-source web-based virtual world platform and related projects

Phoenix web server for Hubs

Accelerating your LLM training to full speed! Made with ❤️ by ServiceNow Research

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

A zero-configuration tool for automatically exposing FastAPI endpoints as Model Context Protocol (MCP) tools.

An Open Source Machine Learning Framework for Everyone

HunyuanVideo-I2V: A Customizable Image-to-Video Model based on HunyuanVideo

Hippy is designed to easily build cross-platform dynamic apps. 👏

A Vue3.x UI components lib for TDesign.

s1: Simple test-time scaling

ncnn is a high-performance neural network inference framework optimized for the mobile platform

Magma: A Foundation Model for Multimodal AI Agents

Players Club is a free Astro template for showcasing music artists—an experimental proof of concept built in collaboration with Alex Tkachev.

Example code snippets and machine learning code for Teachable Machine

High-efficiency floating-point neural network inference operators for mobile, server, and Web