← Edge Attention

AI demonstrations

Explore AI capabilities running in your browser using WebGPU or WebAssembly. These examples illustrate capabilities for custom workflows. Each demo explains its requirements, downloads and limitations; some agent tools also retrieve online sources.

Live now

Deep Research

● live

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

970 MB · desktop · on-device

Live Object Detection

● live

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

27 MB · on-device

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 · on-device

PII Redaction

● live

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

970 MB · desktop · on-device

Meeting Notes

● live

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

1.1 GB · desktop · on-device

Swim Timing

● live

A research detector tracks swimmers on-device. Commercial use requires dataset permissions; not offered as a ready-to-deploy product.

9 MB · on-device

Scanned Document OCR

● live

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

96 MB · on-device

Sensor Anomaly Detection

● live

A model trained on synthetic meter data flags spikes, outages and stuck sensors. An illustrative example, not a field-validated detector.

12 KB · on-device

Table Extraction

● live

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

230 MB · on-device

Voice Fraud Detection

● live

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

125 MB · on-device

AI Guardrails

● live

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

370 MB · on-device

AI Image Detection

● live

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

785 MB · desktop · on-device

In the lab

Depth From a Photo

in the lab

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

19 MB · on-device

Background Removal

in the lab

Clean transparent cut-outs, fully offline.

44 MB · on-device

Live Captions

in the lab

Whisper transcribes your voice as you speak.

41 MB · on-device

Voice Studio

in the lab

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

86 MB · on-device

Offline Chat

in the lab

A streaming chatbot that keeps working in airplane mode.

290 MB · on-device

Vision Q&A

in the lab

Upload an image and ask anything about it.

189 MB · on-device

Anything Recognizer

in the lab

Type your own labels; the camera classifies against them.

153 MB · on-device

Code Assistant

in the lab

A coding copilot with no telemetry.

555 MB · on-device

Photo Upscaler

in the lab

Double the resolution of a blurry photo.

32 MB · on-device

Semantic Search

in the lab

Search any text by meaning as you type.

23 MB · on-device

Demos combine original work and third-party models under their respective licences. Commercial use and deployment requirements are reviewed for each project. Research demonstrations are not guarantees of production accuracy.