XR Blocks is a lightweight WebXR + WebAI library for rapidly prototyping advanced XR and AI experiences.

This repository is an implementation of converting the YOLOv10 object detection model to LiteRT (.tflite) format and deploy it on Android using Google AI Edge for on-device inference.

A hardware implementation of quantized neural network inference in the PyRTL hardware description language.

Web AI

Image Classification, Image Captioning and LLM inference with LiteRT

A list of production-ready models for resource-constrained devices.

A set of tools and examples for converting and utilizing powerful vision models, DINOv3 and EdgeTAM (SAM2), within the ONNX ecosystem.

Graph-based C++ runtime for building and executing AI, ML, and computer vision pipelines across devices.

A maternal health platform empowering ASHA workers with smart data tools to detect high-risk pregnancies, deliver personalized dietary advice, and ensure safer outcomes in rural India.

The core of LiteRT.

Python client for benchmarking and validating ML models on real devices via RunLocal API.

Image Classification with LiteRT

A simple HTTP server based on LiteRT framework.

A tool kits about annotations for LiteRT.

An Android app that helps individuals with hearing impairments by converting environmental sounds into real-time vibration alerts.

Run AI inference in an Android app with llama.cpp, ExecuTorch, LiteRT, ONNX, and more.

Predict Gender in real time by showing your hand in your camera.

A HTTP(S) client base on LiteRT.