A tool for converting ONNX files to LiteRT/TFLite/TensorFlow, PyTorch native code (nn.Module), TorchScript (.pt), state_dict (.pt), Exported Program (.pt2), and Dynamo ONNX. It also supports direct conversion from LiteRT to PyTorch.

PokeClaw (PocketClaw) — first on-device AI that controls your Android phone. Gemma 4, no cloud, no API key. Poke is short for Pocket.

OpenClaw alternative in your pocket

Private on-device AI suite for Android. Fork of Google AI Edge Gallery with llama.cpp, whisper.cpp, stable-diffusion.cpp, GGUF import, voice chat, vision AI, on-device image generation, biometric lock, encrypted history, and CPU/NPU/GPU acceleration.

Flutter plugin for Ultralytics YOLO

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

Run local LLMs like Gemma, Qwen, and LLaMA on Android for offline, private, real-time chat and question answering with LiteRT and ONNX Runtime.

Turn your Android phone into an OpenAI-compatible LLM inference server — Fully local, private and Open Source

Run ml models with both tflite & litert runtimes on edge devices

Swift package for running LiteRT-LM models on iOS. Wraps Google's C API in a clean, async/await Swift interface.

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.

on-device sensitive content blocker for Android. Works across any app powered by a custom-trained on-device AI model.

Image Classification, Image Captioning and LLM inference with LiteRT

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

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

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

Your sovereign, zero-cost AI study companion—running Gemma 4 entirely on your own hardware.

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

Edge Agent Lab is an Android testing platform for evaluating small language model (SLM) agents directly on mobile devices.

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