on-device-ai repositories

Trending repositories tagged on-device-ai, ranked by trending score. Updated daily.

  1. 1
    Edge0-AI/Edge0

    Device-native foundation models: 145B on a laptop, 35B on a phone. Latent MoE, SSD-streamed weights, a router that predicts loads a step ahead. Mac, iPhone, Android, Windows.

    GitHub · C++ · 12,204 stars · 1,890 forks · +101 stars in 24 hours · Trending score 4.37

  2. 2
    cactus-compute/cactus

    Sub-50mb agentic, voice and vision intelligence for consumer devices.

    GitHub · Python · 14,880 stars · 1,049 forks · +34 stars in 24 hours · Trending score 3.06

  3. 3
    AbrahamPaulJ/facefusion-mobile

    FaceFusion for Android. Offline face swap running on the phone's NPU, GPU or CPU. Qualcomm Hexagon (v68 to v81), Vulkan fallback, no server and no upload.

    GitHub · Kotlin · 145 stars · 77 forks · +41 stars in 24 hours · Trending score 2.93

  4. 4
    subhashhhhhh/Lumen

    A photo gallery for Android with the smart features of Google Photos and iPhone Photos. Nothing leaves your phone.

    GitHub · Kotlin · 207 stars · 7 forks · +39 stars in 24 hours · Trending score 2.78

  5. 5
    tetherto/qvac

    Open-source local AI SDK - run AI on-device with no cloud, no API keys. Supports GGUF, RAG, image, music, and video generation, speech-to-text, P2P inference, and more. Cross-platform: Linux, macOS, Windows, Android, iOS.

    GitHub · TypeScript · 814 stars · 170 forks · +25 stars in 24 hours · Trending score 2.69

  6. 6
    AbrahamPaulJ/nightmare-mobile

    On-device, ComfyUI-style node graph for image/video diffusion on Android. Run MiniMax H3 and WAN 2.2 14B on the Qualcomm Hexagon NPU. SD1.5, SDXL, Flux, Z-Image, Anima, Qwen Image 2.1, Krea 2 & MOSS Image. Inpainting, outpainting, ControlNet, LoRA, IP-Adapter & LivePortrait. Fully offline, no server, no account.

    GitHub · Kotlin · 298 stars · 26 forks · +23 stars in 24 hours · Trending score 2.63

  7. 7
    Zyphra/ZONOS3-Mini

    compact zero-shot voice-cloning TTS with state-of-the-art performance, leading voice control, real-time on-device.

    GitHub · Python · 266 stars · 30 forks · +10 stars in 24 hours · Trending score 2.62

  8. 8
    gsamat/amanu

    Records and transcribes online meetings. Automatically

    GitHub · Swift · 254 stars · 48 forks · +24 stars in 24 hours · Trending score 2.50

  9. 9
    RunanywhereAI/runanywhere-sdks

    Production ready toolkit to run AI locally

    GitHub · C++ · 10,354 stars · 422 forks · +21 stars in 24 hours · Trending score 2.40

  10. 10
    NightMean/OlliteRT

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

    GitHub · Kotlin · 647 stars · 99 forks · +26 stars in 24 hours · Trending score 2.37

  11. 11
    yanun0323/Whallm

    DeepSeek-V4-Flash-0731 284B inference in ~25 GB of RAM / Qwen3.8-Next-Flash inference in ~15 GB of RAM on any M-series MacBook

    GitHub · Python · 151 stars · 18 forks · +26 stars in 24 hours · Trending score 2.35

  12. 12
    Sentient-OS-Labs/sentient-os

    An on-device LLM understands your entire life, then proactively offers to get your work done through computer use.

    GitHub · Swift · 777 stars · 81 forks · +14 stars in 24 hours · Trending score 2.33

  13. 13
    ShadowSafin/AndroLLM

    Open-source Android AI using LiteRT-LM with hardware acceleration, cloud providers, memory, and voice.

    GitHub · Kotlin · 121 stars · 8 forks · +20 stars in 24 hours · Trending score 2.28

  14. 14
    google-ai-edge/LiteRT-LM

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

    GitHub · C++ · 6,919 stars · 800 forks · +11 stars in 24 hours · Trending score 2.20

  15. 15
    hikaku-io/hikaku-extension

    Open-source browser extension that flags AI-generated images and video as you browse. Runs entirely on your device. Chrome, Edge and Firefox.

    GitHub · JavaScript · 408 stars · 9 forks · +6 stars in 24 hours · Trending score 2.17

  16. 16
    maxwhipw/marmalade-tts-android

    Native Android TTS app with on-device neural voices and emotion-aware prosody — sister project to marmalade-tts (CLI).

    GitHub · C++ · 122 stars · 10 forks · +22 stars in 24 hours · Trending score 2.15

  17. 17
    0xCoach/TaoSheng

    涛声 TaoSheng:24小时人生上下文记录,用一部手机全天收音 → 转写 → 认人 → AI 整理成待办与记忆,夜里的鼾声、梦话也记录。无需硬件、无需账号,数据只在你手机里。

    GitHub · Kotlin · 440 stars · 64 forks · +5 stars in 24 hours · Trending score 2.06

  18. 18
    callstackincubator/ai

    On-device LLM execution in React Native with Vercel AI SDK compatibility

    GitHub · TypeScript · 1,442 stars · 64 forks · +16 stars in 24 hours · Trending score 2.02

  19. 19
    lokutor-ai/oido

    Oído: open-vocabulary speech recognition on a $5 ESP32-S3, faster than real time. No cloud, no NPU. English + Spanish.

    GitHub · C · 141 stars · 13 forks · +12 stars in 24 hours · Trending score 1.96

  20. 20
    cactus-compute/engine

    2bit quants, kernels and runtime for consumer devices.

    GitHub · C++ · 6,199 stars · 515 forks · +19 stars in 24 hours · Trending score 1.95

  21. 21
    Neywa-Labs/nativ

    Nativ is an open-source local AI app for Mac. It runs open AI models on Apple Silicon, and nothing leaves your Mac.

    GitHub · Swift · 1,613 stars · 117 forks · +9 stars in 24 hours · Trending score 1.93

  22. 22
    coryparrry/Intents

    Intents is a native macOS workbench for evaluating Apple's on-device Foundation Models.

    GitHub · Swift · 19 stars · 0 forks · +13 stars in 24 hours · Trending score 1.92

  23. 23
    drumih/turbo-fieldfare

    Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook

    GitHub · Swift · 7,438 stars · 482 forks · +4 stars in 24 hours · Trending score 1.86

  24. 24
    jammaru/sakutto

    A browser extension for easy on-device translation with a local LLM (PLaMo). Private, free, no server needed.

    GitHub · TypeScript · 282 stars · 33 forks · +4 stars in 24 hours · Trending score 1.84