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

English · German · Spanish · French · Japanese · Korean · Portuguese · Chinese

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

./scripts/adapt_mlange_key.sh

Auto-generated from each app's

meta.json

. Runpython3 scripts/generate_catalog.py

after adding one.

Jump to: 💬 Language & Text · 👁️ Vision · ❤️ Health & Wellbeing · 🔊 Audio · 📈 Forecasting

App	What it does	Model	Platforms	Try it
Brew AI Notes

Gemma-4-E2B

iOS

Model ↗CherryPadLFM2.5-350M

Android

iOS

Model ↗Grammar FixerT5-base

Android

iOS

Model ↗HY-MT TranslatorTencent HY-MT

Android

iOS

Model ↗MedASRMedASR

Android

Model ↗Offline TranslatorTencent HY-MT

Android

iOS

Model ↗PromptGuardLlama Prompt Guard 2

iOS

Model ↗Qwen3 ChatQwen3-4B

Android

iOS

Model ↗SayRightCitrinet-256 (phoneme CTC)

Flutter

Model ↗Text Anonymizertanaos-anonymizer-v1

Android

iOS

Model ↗VoxScribepyannote + Whisper

Flutter

Model ↗Whisper ASRWhisper Tiny

Android

iOS

Model ↗| App | What it does | Model | Platforms | Try it | |---|---|---|---|---| Emotion Recognition |

Emo-AffectNet

Android

iOS

Model ↗Face DetectionBlazeFace

Android

iOS

Model ↗Face LandmarkerMediaPipe

Android

iOS

Model ↗GlyphGoPP-OCRv5 (DBNet + SVTR)

Flutter

Model ↗PlateHawkYOLOv8n

Flutter

Model ↗RedactLensPP-OCRv5 (DBNet + CRNN)

Flutter

Model ↗ShelfSenseYOLO11s (SKU-110K)

Flutter

Model ↗SiteGuardYOLOv8s (PPE)

Flutter

Model ↗SkyScoutYOLOv8s (VisDrone)

Flutter

Model ↗YOLO26YOLO26

Android

iOS

Model ↗YOLOv26-SegYOLOv26-Seg Nano

Android

Model ↗YOLOv8YOLOv8n

Android

iOS

Model ↗| App | What it does | Model | Platforms | Try it | |---|---|---|---|---| Camera Vitals |

EfficientPhys-rPPG

Android

iOS

Model ↗FundusGateMobileNetV2

Flutter

Model ↗GradeVueMobileNetV2

Flutter

Model ↗OraLensYOLO11n

Flutter

Model ↗Skin ClassifierSkin-Cancer ViT

Android

iOS

Model ↗Voice Biomarkerwav2vec2 · YAMNet

Android

iOS

Model ↗Wellbeing Screenerwav2vec2 · Emo-AffectNet

Android

iOS

Model ↗| App | What it does | Model | Platforms | Try it | |---|---|---|---|---| NeuTTS Nano |

NeuTTS Nano

iOS

Model ↗Qwen TTSQwen3-TTS-0.6B

iOS

Model ↗YamNetYAMNet

Android

iOS

Model ↗| App | What it does | Model | Platforms | Try it | |---|---|---|---|---| Chronos Forecast |

Chronos-Bolt

Android

iOS

Model ↗SentryWaveChronos-Bolt-tiny

Flutter

Model ↗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 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

:

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, 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>/

withAndroid/

and/oriOS/

• Add a meta.json

(see any existing app) and aREADME.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.

Built by ZETIC · Powered by Melange

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.

source & further reading

github.com — original article