← Edge Attention

Available models

Every demo downloads a real model into your browser and runs it on your device with WebGPU. No inference servers, no API keys. The download size shown is the entire model.

Live now

Deep Research

● live

An agent plans searches, reads live sources, and writes a cited brief in front of you.

970 MB · desktop · WebGPU

Live Object Detection

● live

EdgeSight-1 draws labelled boxes on your camera feed in real time.

27 MB · WebGPU

Private Document Q&A

● live

Drop a contract or report and ask questions. Indexed and answered on your device with cited passages.

990 MB · desktop · WebGPU

PII Redaction

● live

Strip names, cards, and identifiers on-device before a document leaves your perimeter.

970 MB · desktop · WebGPU

Meeting Notes

● live

Record a memo; two chained models turn it into minutes with action items.

1.1 GB · desktop · WebGPU

Swim Timing

● live

Upload swimming footage; a detector we trained ourselves finds and tracks swimmers on-device.

9 MB · WebGPU

Scanned Document OCR

● live

Upload a scan or photo of a page; two models find and read the text on-device.

96 MB · WebGPU

Sensor Anomaly Detection

● live

A 12 KB model we trained ourselves flags spikes, outages, and stuck sensors in meter data.

12 KB · WebGPU

Table Extraction

● live

Upload a statement or invoice PDF; two models turn its tables into copyable CSV on-device.

230 MB · WebGPU

Voice Fraud Detection

● live

Record or upload a voice clip; EdgeVoice-1 estimates on-device whether it is cloned or human.

125 MB · WebGPU

AI Guardrails

● live

Screen text for prompt-injection attacks and abusive content before it reaches a model.

370 MB · WebGPU

AI Image Detection

● live

Upload an image; EdgeVerify-2 estimates on-device whether it was generated or captured.

785 MB · desktop · WebGPU

In the lab

Depth From a Photo

in the lab

A flat photo becomes a 3D scene you can tilt.

19 MB · WebGPU

Background Removal

in the lab

Clean transparent cut-outs, fully offline.

44 MB · WebGPU

Live Captions

in the lab

Whisper transcribes your voice as you speak.

41 MB · WebGPU

Voice Studio

in the lab

Type anything; Kokoro speaks it in 56 voices across 8 languages.

86 MB · WebGPU

Offline Chat

in the lab

A streaming chatbot that keeps working in airplane mode.

290 MB · WebGPU

Vision Q&A

in the lab

Upload an image and ask anything about it.

189 MB · WebGPU

Anything Recognizer

in the lab

Type your own labels; the camera classifies against them.

153 MB · WebGPU

Code Assistant

in the lab

A coding copilot with no telemetry.

555 MB · WebGPU

Photo Upscaler

in the lab

Double the resolution of a blurry photo.

32 MB · WebGPU

Semantic Search

in the lab

Search any text by meaning as you type.

23 MB · WebGPU

All demo models are Apache-2.0 licensed. Demos ship one at a time; the rest of the lab is on its way.