{"slug": "open-source-on-device-ai-apps-and-counting-no-cloud-works-offline", "title": "Open source on-device AI apps (and counting), no cloud, works offline", "summary": "ZETIC.ai released an open-source catalog of on-device AI apps that run entirely on a phone's NPU without cloud connectivity, eliminating compliance costs and per-token fees. The collection includes finished apps for chat, translation, vision, health, voice, and forecasting, all operating offline with zero marginal cost.", "body_md": "**English** ·\n[German](/zetic-ai/awesome-on-device-ai-apps/blob/main/translations/README.de.md) ·\n[Spanish](/zetic-ai/awesome-on-device-ai-apps/blob/main/translations/README.es.md) ·\n[French](/zetic-ai/awesome-on-device-ai-apps/blob/main/translations/README.fr.md) ·\n[Japanese](/zetic-ai/awesome-on-device-ai-apps/blob/main/translations/README.ja.md) ·\n[Korean](/zetic-ai/awesome-on-device-ai-apps/blob/main/translations/README.ko.md) ·\n[Portuguese](/zetic-ai/awesome-on-device-ai-apps/blob/main/translations/README.pt.md) ·\n[Chinese](/zetic-ai/awesome-on-device-ai-apps/blob/main/translations/README.zh.md)\n\n**No compliance wall · $0 at any scale · Data never leaves the device · Works offline**\n\n💬 Chat · 🌐 Translate · 👁️ Vision · ❤️ Health · 🎙️ Voice · 📈 Forecasting\n\n⚡ Powered by\n\n**Melange**, the on-device NPU runtime\n\nEvery app here runs the model on the phone itself. Nothing goes to a server. That one fact rewrites the economics:\n\n- 🛡️\n**No compliance wall.** No user data in the cloud means no GDPR, HIPAA, or data-residency blocker between you and launch. Put AI into health, finance, and enterprise products, and actually charge for it. - 💸\n**$0 marginal cost.** No per-token bill, no inference servers. Your margins hold as you scale from 1 to 10 million users. - 🔒\n**Private by design.** Nothing leaves the device, so there is no cloud dataset to breach, leak, or get audited over. - ⚡\n**Instant and offline.** Runs on the phone's NPU with no network round-trip, on a plane, a subway, or a factory floor with no signal.\n\nAnd these are not snippets. Every folder is a finished app you clone and run on a real device today.\n\nPick any app, clone, and run it on a real device. No ML setup, no model conversion, no C++.\n\n```\ngit clone https://github.com/zetic-ai/awesome-on-device-ai-apps.git\ncd awesome-on-device-ai-apps\n\n# A free key lets the app pull its NPU-optimized weights on first launch\n# (30 seconds, no card): mlange.zetic.ai -> Settings -> Personal Access Token\n./scripts/adapt_mlange_key.sh\n\n# Open an app on a REAL device (the NPU isn't in the simulator):\n#   Android:  apps/<AppName>/Android    in Android Studio\n#   iOS:      apps/<AppName>/iOS        in Xcode\n#   Flutter:  cd apps/<AppName>/Flutter && flutter run\n```\n\nAuto-generated from each app's\n\n`meta.json`\n\n. Run`python3 scripts/generate_catalog.py`\n\nafter adding one.\n\n**Jump to:** 💬 [Language & Text](#cat-language-text) · 👁️ [Vision](#cat-vision) · ❤️ [Health & Wellbeing](#cat-health-wellbeing) · 🔊 [Audio](#cat-audio) · 📈 [Forecasting](#cat-forecasting)\n\n| App | What it does | Model | Platforms | Try it |\n|---|---|---|---|---|\nBrew AI Notes |\n\n`Gemma-4-E2B`\n\n`iOS`\n\n[Model ↗](https://mlange.zetic.ai/p/changgeun/gemma-4-E2B-it)**CherryPad**`LFM2.5-350M`\n\n`Android`\n\n`iOS`\n\n[Model ↗](https://mlange.zetic.ai/p/Steve/LFM2.5_350M)**Grammar Fixer**`T5-base`\n\n`Android`\n\n`iOS`\n\n[Model ↗](https://mlange.zetic.ai/p/Team_ZETIC/t5-base-grammar-correction)**HY-MT Translator**`Tencent HY-MT`\n\n`Android`\n\n`iOS`\n\n[Model ↗](https://mlange.zetic.ai/p/vaibhav-zetic/tencent_HY-MT)**MedASR**`MedASR`\n\n`Android`\n\n[Model ↗](https://mlange.zetic.ai/p/vaibhav-zetic/Medasr)**Offline Translator**`Tencent HY-MT`\n\n`Android`\n\n`iOS`\n\n[Model ↗](https://mlange.zetic.ai/p/vaibhav-zetic/tencent_HY-MT)**PromptGuard**`Llama Prompt Guard 2`\n\n`iOS`\n\n[Model ↗](https://mlange.zetic.ai/p/jathin-zetic/llama_prompt_guard_2)**Qwen3 Chat**`Qwen3-4B`\n\n`Android`\n\n`iOS`\n\n[Model ↗](https://mlange.zetic.ai/p/Qwen/Qwen3-4B)**SayRight**`Citrinet-256 (phoneme CTC)`\n\n`Flutter`\n\n[Model ↗](https://mlange.zetic.ai/p/ajayshah/PronunciationScoring)**Text Anonymizer**`tanaos-anonymizer-v1`\n\n`Android`\n\n`iOS`\n\n[Model ↗](https://mlange.zetic.ai/p/Steve/text-anonymizer-v1)**VoxScribe**`pyannote + Whisper`\n\n`Flutter`\n\n[Model ↗](https://mlange.zetic.ai/p/ajayshah/VoxScribe-whisper-decoder)**Whisper ASR**`Whisper Tiny`\n\n`Android`\n\n`iOS`\n\n[Model ↗](https://mlange.zetic.ai/p/OpenAI/whisper-tiny-decoder)| App | What it does | Model | Platforms | Try it |\n|---|---|---|---|---|\nEmotion Recognition |\n\n`Emo-AffectNet`\n\n`Android`\n\n`iOS`\n\n[Model ↗](https://mlange.zetic.ai/p/ElenaRyumina/FaceEmotionRecognition)**Face Detection**`BlazeFace`\n\n`Android`\n\n`iOS`\n\n[Model ↗](https://mlange.zetic.ai/p/google/MediaPipe-Face-Detection)**Face Landmarker**`MediaPipe`\n\n`Android`\n\n`iOS`\n\n[Model ↗](https://mlange.zetic.ai/p/google/MediaPipe-Face-Landmark)**GlyphGo**`PP-OCRv5 (DBNet + SVTR)`\n\n`Flutter`\n\n[Model ↗](https://mlange.zetic.ai/p/ajayshah/SignTranslate_Detect)**PlateHawk**`YOLOv8n`\n\n`Flutter`\n\n[Model ↗](https://mlange.zetic.ai/p/ajayshah/VehiclePlateYOLO)**RedactLens**`PP-OCRv5 (DBNet + CRNN)`\n\n`Flutter`\n\n[Model ↗](https://mlange.zetic.ai/p/ajayshah/LiveDocRedact_Detect)**ShelfSense**`YOLO11s (SKU-110K)`\n\n`Flutter`\n\n[Model ↗](https://mlange.zetic.ai/p/ajayshah/ShelfScanYOLO)**SiteGuard**`YOLOv8s (PPE)`\n\n`Flutter`\n\n[Model ↗](https://mlange.zetic.ai/p/ajayshah/SafetyPPEYOLO)**SkyScout**`YOLOv8s (VisDrone)`\n\n`Flutter`\n\n[Model ↗](https://mlange.zetic.ai/p/ajayshah/AerialDetectYOLO)**YOLO26**`YOLO26`\n\n`Android`\n\n`iOS`\n\n[Model ↗](https://mlange.zetic.ai/p/Team_ZETIC/YOLO26)**YOLOv26-Seg**`YOLOv26-Seg Nano`\n\n`Android`\n\n[Model ↗](https://mlange.zetic.ai/p/vaibhav-zetic/Yolov26-Seg-Nano)**YOLOv8**`YOLOv8n`\n\n`Android`\n\n`iOS`\n\n[Model ↗](https://mlange.zetic.ai/p/Ultralytics/YOLOv8n)| App | What it does | Model | Platforms | Try it |\n|---|---|---|---|---|\nCamera Vitals |\n\n`EfficientPhys-rPPG`\n\n`Android`\n\n`iOS`\n\n[Model ↗](https://mlange.zetic.ai/p/realtonypark/EfficientPhys-rPPG_camera_vitals)**FundusGate**`MobileNetV2`\n\n`Flutter`\n\n[Model ↗](https://mlange.zetic.ai/p/ajayshah/RetinaDRScreen)**GradeVue**`MobileNetV2`\n\n`Flutter`\n\n[Model ↗](https://mlange.zetic.ai/p/ajayshah/RetinaDRGrade)**OraLens**`YOLO11n`\n\n`Flutter`\n\n[Model ↗](https://mlange.zetic.ai/p/ajayshah/DentalXRayDetect)**Skin Classifier**`Skin-Cancer ViT`\n\n`Android`\n\n`iOS`\n\n[Model ↗](https://mlange.zetic.ai/p/realtonypark/Skin_Cancer-Image_Classification)**Voice Biomarker**`wav2vec2 · YAMNet`\n\n`Android`\n\n`iOS`\n\n[Model ↗](https://mlange.zetic.ai/p/realtonypark/Wav2Vec2-Base_Emotion-Recognition)**Wellbeing Screener**`wav2vec2 · Emo-AffectNet`\n\n`Android`\n\n`iOS`\n\n[Model ↗](https://mlange.zetic.ai/p/realtonypark/Wav2Vec2-Base_Emotion-Recognition)| App | What it does | Model | Platforms | Try it |\n|---|---|---|---|---|\nNeuTTS Nano |\n\n`NeuTTS Nano`\n\n`iOS`\n\n[Model ↗](https://mlange.zetic.ai/p/jathin-zetic/neutts_nano)**Qwen TTS**`Qwen3-TTS-0.6B`\n\n`iOS`\n\n[Model ↗](https://mlange.zetic.ai/p/jathin-zetic/qwen_tts06b_talker)**YamNet**`YAMNet`\n\n`Android`\n\n`iOS`\n\n[Model ↗](https://mlange.zetic.ai/p/google/Sound%20Classification%28YAMNET%29)| App | What it does | Model | Platforms | Try it |\n|---|---|---|---|---|\nChronos Forecast |\n\n`Chronos-Bolt`\n\n`Android`\n\n`iOS`\n\n[Model ↗](https://mlange.zetic.ai/p/Team_ZETIC/Chronos-balt-tiny)**SentryWave**`Chronos-Bolt-tiny`\n\n`Flutter`\n\n[Model ↗](https://mlange.zetic.ai/p/ajayshah/SensorForecastTS)Claude Code, Codex, and Cursor will vibe-code you a web app in minutes. Ask them for an app that runs a model on the phone's NPU and they stall, because on-device deployment is not something they know how to do.\n\nThat is the gap [ Melange](https://mlange.zetic.ai) fills, and it is the easiest way in the world to put AI on-device today.\n\n**Every app in this repo was built the same way: generate the integration code with Melange, paste it in, done.** Copy a use case from here and the on-device feature drops straight into your app, the same vibe-coding loop you already use.\n\nDropping it into an existing project is about 3 lines:\n\n**Android**, in `build.gradle.kts`\n\n:\n\n```\ndependencies { implementation(\"com.zeticai.mlange:mlange:+\") }\nval model = ZeticMLangeModel(context = this, tokenKey = \"YOUR_KEY\", modelName = \"Team_ZETIC/YOLO26\")\nval outputs = model.run(inputs)   // NPU-accelerated, on-device\n```\n\n**iOS**, via Swift Package Manager → `https://github.com/zetic-ai/ZeticMLangeiOS.git`\n\n:\n\n``` js\nlet model = try ZeticMLangeModel(tokenKey: \"YOUR_KEY\", name: \"Team_ZETIC/YOLO26\", version: 1)\nlet outputs = try model.run(inputs: inputs)\n```\n\nBring your own model: upload it to [Melange](https://mlange.zetic.ai), it converts and NPU-optimizes automatically, then hands you back a phone-ready build in about an hour, not months of hardware tuning.\n\nThis gallery grows by contribution, and the bar is one question: **would a stranger clone this and actually use it?**\n\n- Drop your app in\n`apps/<YourApp>/`\n\nwith`Android/`\n\nand/or`iOS/`\n\n- Add a\n`meta.json`\n\n(see any existing app) and a`README.md`\n\n- Run\n`python3 scripts/generate_catalog.py`\n\nto add it to the catalog - Prove it runs on a real device (demo GIF in the PR)\n\nFull guide → ** CONTRIBUTING.md**. Questions →\n\n[Discord](https://discord.gg/gqhDWfZbgU).\n\nBuilt by [ZETIC](https://zetic.ai) · Powered by [Melange](https://mlange.zetic.ai)\n\n**If a phone-native AI app made you go \"wait, that runs offline?\", then ⭐ star it. It's how the next dev finds it.**\n\nApp source is **Apache 2.0**: use it commercially or privately, however you like. The Melange SDK itself is a proprietary library under the ZETIC [Terms of Service](https://zetic.ai/terms).", "url": "https://wpnews.pro/news/open-source-on-device-ai-apps-and-counting-no-cloud-works-offline", "canonical_source": "https://github.com/zetic-ai/awesome-on-device-ai-apps", "published_at": "2026-07-13 20:36:54+00:00", "updated_at": "2026-07-13 21:07:40.453910+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-products", "ai-tools", "ai-infrastructure"], "entities": ["ZETIC.ai", "Melange", "Gemma", "Qwen", "Whisper", "Tencent HY-MT", "Llama", "Citrinet"], "alternates": {"html": "https://wpnews.pro/news/open-source-on-device-ai-apps-and-counting-no-cloud-works-offline", "markdown": "https://wpnews.pro/news/open-source-on-device-ai-apps-and-counting-no-cloud-works-offline.md", "text": "https://wpnews.pro/news/open-source-on-device-ai-apps-and-counting-no-cloud-works-offline.txt", "jsonld": "https://wpnews.pro/news/open-source-on-device-ai-apps-and-counting-no-cloud-works-offline.jsonld"}}