mobile-ai

lcpp is a dart implementation of llama.cpp used by the mobile artificial intelligence distribution (maid)

MineGPT 是一个基于Kotlin Multiplatform 开发的本地小型语言模型(SLM)对话应用; MineGPT is a lightweight local SLM (Small Language Model) chat application built with Kotlin Multiplatform. It aims to provide a cross-platform and user-friendly AI assistant experience.

Custom llama.cpp fork with character intelligence engine: control vectors, attention bias, head rescaling, attention temperature, fast weight memory

Protect your Machine Learning model in your Flutter application.

Real-ESRGAN model deployed on Android using NCNN (C++/JNI) and ExecuTorch (Java) for real-time image super-resolution in dermatology, with reproducible benchmarking (PSNR, SSIM, MSE, LPIPS).

HarmonyOS NEXT native Gemma 4 MNN on-device LLM chat demo

Gemma 4 architecture support for QVAC-Fabric llama.cpp fork

Real-time pothole detection Android application using computer vision, OpenCV, and native C++ processing. Developed during a designathon that led to an Ericsson internship.

On-device AI camera guard you program in one English sentence — Arm CPU only (hand-written NEON gate + KleidiAI INT4 SmolVLM), 100% local, no cloud/NVIDIA. Runs on a spare iPhone or a Mac webcam. Arm AI Optimization Challenge · Track 3 Mobile AI.

🚀 LiteRT-LM: Google's production-ready, high-performance inference framework for deploying Large Language Models on edge devices.

Spatial intelligence framework for persistent object counting using ML Kit, OpenCV and adaptive spatial anchoring on Android.

LiteRT continues the legacy of TensorFlow Lite as the trusted, high-performance runtime for on-device AI. Now with LiteRT Next, we're expanding our vision with a new generation of APIs designed for superior performance and simplified hardware acceleration. Discover what's next for on-device AI.