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.
Run local LLMs like Gemma, Qwen, and LLaMA on Android for offline, private, real-time chat and question answering with LiteRT and ONNX Runtime.
Swift package for running LiteRT-LM models on iOS. Wraps Google's C API in a clean, async/await Swift interface.
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 NPU/TPU acceleration.
Turn your Android phone into an OpenAI-compatible LLM inference server — Fully local, private and Open Source
Run LLM inference in an Android app with llama.cpp, ExecuTorch, LiteRT, ONNX, and more.
Edge Agent Lab is an Android testing platform for evaluating small language model (SLM) agents directly on mobile devices.
LiteRT-LM model inference support for Unity Android and Meta Quest apps.
Rust bindings for LiteRT, successor to TensorFlow Lite. is Google's On-device framework for high-performance ML & GenAI deployment on edge platforms, via efficient conversion, runtime, and optimization
Agent Skills for on-device ML: FunctionGemma fine-tuning, LiteRT-LM export, and more. Compatible with Claude Code, Codex, and Gemini CLI.
React Native module for on-device LLM inference using LiteRT/MediaPipe. Supports Gemma 3n and other compatible models with AI SDK compatible API
Offline Android object detection app using LiteRT (Google AI Edge). Pick any photo from gallery → instant bounding boxes with labels & confidence scores. Built with Jetpack Compose + Clean Architecture.
Open-source voice assistant for Android — Gemma 4 E2B on-device with native audio input and tool calling. A privacy-first alternative to Google Assistant: no cloud, no account, no telemetry.
Android chat app that runs AI models directly on your phone - no internet, no cloud, nothing leaving your device, ensuring total privacy.
A Flutter application demonstrating on-device multimodal AI inference using Google's LiteRT-LM via a custom JNI bridge using jnigen.
Add a description, image, and links to the litert-lm topic page so that developers can more easily learn about it.
To associate your repository with the litert-lm topic, visit your repo's landing page and select "manage topics."