# Open source on-device AI apps (and counting), no cloud, works offline

> Source: <https://github.com/zetic-ai/awesome-on-device-ai-apps>
> Published: 2026-07-13 20:36:54+00:00

**English** ·
[German](/zetic-ai/awesome-on-device-ai-apps/blob/main/translations/README.de.md) ·
[Spanish](/zetic-ai/awesome-on-device-ai-apps/blob/main/translations/README.es.md) ·
[French](/zetic-ai/awesome-on-device-ai-apps/blob/main/translations/README.fr.md) ·
[Japanese](/zetic-ai/awesome-on-device-ai-apps/blob/main/translations/README.ja.md) ·
[Korean](/zetic-ai/awesome-on-device-ai-apps/blob/main/translations/README.ko.md) ·
[Portuguese](/zetic-ai/awesome-on-device-ai-apps/blob/main/translations/README.pt.md) ·
[Chinese](/zetic-ai/awesome-on-device-ai-apps/blob/main/translations/README.zh.md)

**No compliance wall · $0 at any scale · Data never leaves the device · Works offline**

💬 Chat · 🌐 Translate · 👁️ Vision · ❤️ Health · 🎙️ Voice · 📈 Forecasting

⚡ Powered by

**Melange**, the on-device NPU runtime

Every app here runs the model on the phone itself. Nothing goes to a server. That one fact rewrites the economics:

- 🛡️
**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. - 💸
**$0 marginal cost.** No per-token bill, no inference servers. Your margins hold as you scale from 1 to 10 million users. - 🔒
**Private by design.** Nothing leaves the device, so there is no cloud dataset to breach, leak, or get audited over. - ⚡
**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.

And these are not snippets. Every folder is a finished app you clone and run on a real device today.

Pick any app, clone, and run it on a real device. No ML setup, no model conversion, no C++.

```
git clone https://github.com/zetic-ai/awesome-on-device-ai-apps.git
cd awesome-on-device-ai-apps

# A free key lets the app pull its NPU-optimized weights on first launch
# (30 seconds, no card): mlange.zetic.ai -> Settings -> Personal Access Token
./scripts/adapt_mlange_key.sh

# Open an app on a REAL device (the NPU isn't in the simulator):
#   Android:  apps/<AppName>/Android    in Android Studio
#   iOS:      apps/<AppName>/iOS        in Xcode
#   Flutter:  cd apps/<AppName>/Flutter && flutter run
```

Auto-generated from each app's

`meta.json`

. Run`python3 scripts/generate_catalog.py`

after adding one.

**Jump to:** 💬 [Language & Text](#cat-language-text) · 👁️ [Vision](#cat-vision) · ❤️ [Health & Wellbeing](#cat-health-wellbeing) · 🔊 [Audio](#cat-audio) · 📈 [Forecasting](#cat-forecasting)

| App | What it does | Model | Platforms | Try it |
|---|---|---|---|---|
Brew AI Notes |

`Gemma-4-E2B`

`iOS`

[Model ↗](https://mlange.zetic.ai/p/changgeun/gemma-4-E2B-it)**CherryPad**`LFM2.5-350M`

`Android`

`iOS`

[Model ↗](https://mlange.zetic.ai/p/Steve/LFM2.5_350M)**Grammar Fixer**`T5-base`

`Android`

`iOS`

[Model ↗](https://mlange.zetic.ai/p/Team_ZETIC/t5-base-grammar-correction)**HY-MT Translator**`Tencent HY-MT`

`Android`

`iOS`

[Model ↗](https://mlange.zetic.ai/p/vaibhav-zetic/tencent_HY-MT)**MedASR**`MedASR`

`Android`

[Model ↗](https://mlange.zetic.ai/p/vaibhav-zetic/Medasr)**Offline Translator**`Tencent HY-MT`

`Android`

`iOS`

[Model ↗](https://mlange.zetic.ai/p/vaibhav-zetic/tencent_HY-MT)**PromptGuard**`Llama Prompt Guard 2`

`iOS`

[Model ↗](https://mlange.zetic.ai/p/jathin-zetic/llama_prompt_guard_2)**Qwen3 Chat**`Qwen3-4B`

`Android`

`iOS`

[Model ↗](https://mlange.zetic.ai/p/Qwen/Qwen3-4B)**SayRight**`Citrinet-256 (phoneme CTC)`

`Flutter`

[Model ↗](https://mlange.zetic.ai/p/ajayshah/PronunciationScoring)**Text Anonymizer**`tanaos-anonymizer-v1`

`Android`

`iOS`

[Model ↗](https://mlange.zetic.ai/p/Steve/text-anonymizer-v1)**VoxScribe**`pyannote + Whisper`

`Flutter`

[Model ↗](https://mlange.zetic.ai/p/ajayshah/VoxScribe-whisper-decoder)**Whisper ASR**`Whisper Tiny`

`Android`

`iOS`

[Model ↗](https://mlange.zetic.ai/p/OpenAI/whisper-tiny-decoder)| App | What it does | Model | Platforms | Try it |
|---|---|---|---|---|
Emotion Recognition |

`Emo-AffectNet`

`Android`

`iOS`

[Model ↗](https://mlange.zetic.ai/p/ElenaRyumina/FaceEmotionRecognition)**Face Detection**`BlazeFace`

`Android`

`iOS`

[Model ↗](https://mlange.zetic.ai/p/google/MediaPipe-Face-Detection)**Face Landmarker**`MediaPipe`

`Android`

`iOS`

[Model ↗](https://mlange.zetic.ai/p/google/MediaPipe-Face-Landmark)**GlyphGo**`PP-OCRv5 (DBNet + SVTR)`

`Flutter`

[Model ↗](https://mlange.zetic.ai/p/ajayshah/SignTranslate_Detect)**PlateHawk**`YOLOv8n`

`Flutter`

[Model ↗](https://mlange.zetic.ai/p/ajayshah/VehiclePlateYOLO)**RedactLens**`PP-OCRv5 (DBNet + CRNN)`

`Flutter`

[Model ↗](https://mlange.zetic.ai/p/ajayshah/LiveDocRedact_Detect)**ShelfSense**`YOLO11s (SKU-110K)`

`Flutter`

[Model ↗](https://mlange.zetic.ai/p/ajayshah/ShelfScanYOLO)**SiteGuard**`YOLOv8s (PPE)`

`Flutter`

[Model ↗](https://mlange.zetic.ai/p/ajayshah/SafetyPPEYOLO)**SkyScout**`YOLOv8s (VisDrone)`

`Flutter`

[Model ↗](https://mlange.zetic.ai/p/ajayshah/AerialDetectYOLO)**YOLO26**`YOLO26`

`Android`

`iOS`

[Model ↗](https://mlange.zetic.ai/p/Team_ZETIC/YOLO26)**YOLOv26-Seg**`YOLOv26-Seg Nano`

`Android`

[Model ↗](https://mlange.zetic.ai/p/vaibhav-zetic/Yolov26-Seg-Nano)**YOLOv8**`YOLOv8n`

`Android`

`iOS`

[Model ↗](https://mlange.zetic.ai/p/Ultralytics/YOLOv8n)| App | What it does | Model | Platforms | Try it |
|---|---|---|---|---|
Camera Vitals |

`EfficientPhys-rPPG`

`Android`

`iOS`

[Model ↗](https://mlange.zetic.ai/p/realtonypark/EfficientPhys-rPPG_camera_vitals)**FundusGate**`MobileNetV2`

`Flutter`

[Model ↗](https://mlange.zetic.ai/p/ajayshah/RetinaDRScreen)**GradeVue**`MobileNetV2`

`Flutter`

[Model ↗](https://mlange.zetic.ai/p/ajayshah/RetinaDRGrade)**OraLens**`YOLO11n`

`Flutter`

[Model ↗](https://mlange.zetic.ai/p/ajayshah/DentalXRayDetect)**Skin Classifier**`Skin-Cancer ViT`

`Android`

`iOS`

[Model ↗](https://mlange.zetic.ai/p/realtonypark/Skin_Cancer-Image_Classification)**Voice Biomarker**`wav2vec2 · YAMNet`

`Android`

`iOS`

[Model ↗](https://mlange.zetic.ai/p/realtonypark/Wav2Vec2-Base_Emotion-Recognition)**Wellbeing Screener**`wav2vec2 · Emo-AffectNet`

`Android`

`iOS`

[Model ↗](https://mlange.zetic.ai/p/realtonypark/Wav2Vec2-Base_Emotion-Recognition)| App | What it does | Model | Platforms | Try it |
|---|---|---|---|---|
NeuTTS Nano |

`NeuTTS Nano`

`iOS`

[Model ↗](https://mlange.zetic.ai/p/jathin-zetic/neutts_nano)**Qwen TTS**`Qwen3-TTS-0.6B`

`iOS`

[Model ↗](https://mlange.zetic.ai/p/jathin-zetic/qwen_tts06b_talker)**YamNet**`YAMNet`

`Android`

`iOS`

[Model ↗](https://mlange.zetic.ai/p/google/Sound%20Classification%28YAMNET%29)| App | What it does | Model | Platforms | Try it |
|---|---|---|---|---|
Chronos Forecast |

`Chronos-Bolt`

`Android`

`iOS`

[Model ↗](https://mlange.zetic.ai/p/Team_ZETIC/Chronos-balt-tiny)**SentryWave**`Chronos-Bolt-tiny`

`Flutter`

[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.

That is the gap [ Melange](https://mlange.zetic.ai) fills, and it is the easiest way in the world to put AI on-device today.

**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.

Dropping it into an existing project is about 3 lines:

**Android**, in `build.gradle.kts`

:

```
dependencies { implementation("com.zeticai.mlange:mlange:+") }
val model = ZeticMLangeModel(context = this, tokenKey = "YOUR_KEY", modelName = "Team_ZETIC/YOLO26")
val outputs = model.run(inputs)   // NPU-accelerated, on-device
```

**iOS**, via Swift Package Manager → `https://github.com/zetic-ai/ZeticMLangeiOS.git`

:

``` js
let model = try ZeticMLangeModel(tokenKey: "YOUR_KEY", name: "Team_ZETIC/YOLO26", version: 1)
let outputs = try model.run(inputs: inputs)
```

Bring 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.

This gallery grows by contribution, and the bar is one question: **would a stranger clone this and actually use it?**

- Drop your app in
`apps/<YourApp>/`

with`Android/`

and/or`iOS/`

- Add a
`meta.json`

(see any existing app) and a`README.md`

- Run
`python3 scripts/generate_catalog.py`

to add it to the catalog - Prove it runs on a real device (demo GIF in the PR)

Full guide → ** CONTRIBUTING.md**. Questions →

[Discord](https://discord.gg/gqhDWfZbgU).

Built by [ZETIC](https://zetic.ai) · Powered by [Melange](https://mlange.zetic.ai)

**If a phone-native AI app made you go "wait, that runs offline?", then ⭐ star it. It's how the next dev finds it.**

App 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).