google

Agent Skills for Google products and technologies — composable capability files for coding agents.

Google's Python library for extracting structured data from unstructured text using LLMs, with precise source grounding and interactive visualization.

Google's open-source Python toolkit for building, evaluating, and deploying production-grade AI agents with full control over the agent loop.

Google's real-time physically-based rendering engine for Android, iOS, desktop, and WebGL2 — production-grade 3D graphics for apps.

AI-powered file type detection tool that identifies file formats with 99% accuracy in milliseconds using a highly optimized deep learning model. Processes hundreds of billions of files weekly for Google services and supports 200+ content types.

Google's open-source Go toolkit for building, evaluating, and deploying production-grade AI agents — the Go counterpart to adk-python.

Google's library that automatically turns any Python object into a command-line interface — no argparse boilerplate.

Google's JavaScript scripting tool with $`shell` template literals, top-level await, and fetch — a friendlier alternative to Bash for Node.js developers.

Google's web component for easily displaying interactive 3D models on the web and in AR — one HTML tag, no Three.js required.

Google's neural network library for JAX — flexible by design, used by Gemini, AlphaFold, and most JAX-based research projects.

Google's tool that upgrades npm/pnpm/yarn scripts to be smarter and more efficient — incremental builds, cross-package dependencies, watch mode.

Google's lightweight, standalone C++ inference engine for Gemma models — runs Gemma on CPU with no dependencies, no GPU required.

Google's official PyTorch implementation of the Gemma open-weight models — load, fine-tune, and serve from idiomatic PyTorch.