On-device, real-time multimodal AI. Have natural voice and vision conversations with an AI that runs entirely on your machine. Powered by Gemma 4 E2B and Kokoro.

Give AI coding agents eyes. Records browser sessions, captures screenshots, collects errors, and bundles proof artifacts — so humans can verify what the agent built.

AI agents running research on single-GPU nanochat training automatically

sub-500ms latency phone agent orchestration

Sample code and notebooks for Generative AI on Google Cloud, with Gemini on Vertex AI

Voice calls from Twilio with Gemini's Live API with a nice streaming pipeline

This project demonstrates a real-time voice conversation using Twilio (over phone) and Google's Gemini Multimodal Live API (via Vertex AI).

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

LeKiwi - Low-Cost Mobile Manipulator

Making a mini version of the BDX droid. https://discord.gg/UtJZsgfQGe

A Verilog synthesis flow for Minecraft redstone circuits

Have a natural, spoken conversation with AI!

A monorepo template for building webapps - perfect for LLMs

Examples and guides for using the VLM Run API

Deploys apps to Cloud Run, along with option to map custom domain

Creates one or more service accounts and grants them basic roles

Example code for bootstrapping trust between Terraform Cloud and cloud providers in order to use TFC's Workload Identity

A companion repository to my Cloud Run with Google Sheets series

Open-source platform for extracting structured data from documents using AI.

Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama mode…

Instant is the best backend for AI-coded apps. You get auth, permissions, storage, presence, and streams — everything you need to ship apps your users will love.

real time face swap and one-click video deepfake with only a single image

Operating system for single function smart frames

Inference Llama 2 in one file of pure C

This is the Rust course used by the Android team at Google. It provides you the material to quickly teach Rust.

Interact with your documents using the power of GPT, 100% privately, no data leaks

Numbers every LLM developer should know

OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.