ondevice-ai

The Swiss Army Knife of Offline AI. Chat, see, speak, and generate images on your phone or Mac — GGUF LLMs, vision, Whisper speech-to-text, Stable Diffusion, tool calling, and local-network servers. Runs on your CPU, GPU, or NPU. No account, no API key, zero data leaves your device.

The most advanced, fully offline client-side AI suite on Android today.

🎨 Multiplatform AI image generation app powered by Stable Diffusion • Built with Kotlin Multiplatform & Compose • Supports SDXL, FLUX, SD3 & more • Native performance via C++/JNI • Android/iOS & Desktop ready

Runtime protection for AI agents

Distributed 56M-parameter LLM inference across 3 ESP32-S3 boards via ESP-NOW , Split-PLE + KV cache, fully offline.

All-in-one offline document viewer for Android with OCR and desktop-class rendering — private, open-source, zero tracking

Android application allows you to use ai on device

A high-performance, private, on-device AI chat client built with Flutter. AstraLM runs Large Language Models (LLMs) and Vision models 100% locally on device hardware (CPU & GPU) with zero data leaving your phone.(until you choose to use cloud model which is completely OPTIONAL)

Private. Local. Yours. Cross-platform On-device LLM & Agent Client powered by LiteRT-LM & Compose Multiplatform.

AI-powered disaster response platform with offline-first architecture using Gemma 3n. Provides computer vision hazard detection, voice analysis with emergency keywords, PDF report generation, and multi-user coordination - all working without internet access.

Rust bindings for Qualcomm GenieX SDK - Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code.

Online Self-Distillation Fine-Tuning (SDFT) for Small Language Models (SLM)

Harness tacit knowledge into the context of AI agent with on device always-on transcription

On-device AI framework inspired by LangChain, purpose-built for mobile. Build, compose, and extend AI features using platform-native models — all processing happens locally on the device.

 UMC 동아리 운영 iOS 앱 — 출석·스터디·커리큘럼 관리. SwiftUI, Clean Architecture, 모듈화.

Curated resource for mobile teams shipping on-device LLMs — runtime benchmarks, model picks, GDPR-friendly architecture, and real production use cases.

Ojas is a production-grade Android application that measures heart rate from live camera feed using remote photoplethysmography (rPPG) technology. The app leverages Arm Neon SIMD for signal processing and NNAPI for AI-powered signal refinement, achieving real-time performance on mobile devices.

On-device DPO + QLoRA fine-tuning pipeline to ground a SLM in oil-and-gas jargons. Cloudera AMP: https://cloudera.github.io/Applied-ML-Prototypes/#/community

[SenSys '26] PELM: Power Efficient On-Device LLM Inference with Speculative Decoding and Dynamic Voltage Frequency Scaling