SYSTEM ARCHITECTURETHE PROJECT
A browser-extension integration for captured pixels and local model inference.
The extension demonstrates an end-to-end browser ML boundary: capture visible pixels, queue work in a service worker, verify the model asset and run inference in an offscreen context. The integration explores GPU and WASM paths while keeping the model score distinct from a validated classification.
- Manifest V3 capture and bounded work queue
- Hash-verified ONNX model loading
- WebGPU / WASM inference and a score badge
Integration prototype. Its uncalibrated score is not presented as a reliable verdict about an image's origin.
UNDER THE SURFACE
How it fits together.
The service worker manages work and an offscreen context owns model execution. The returned score is an integration output, not a calibrated authenticity decision.
Swipe or scroll the diagram to inspect it. The components are also listed below.
- 01Visible pixels
Explicit browser capture
- 02Service worker
Bounded request queue
- 03Offscreen context
Isolated inference host
- 04Verified model
Hash-checked ONNX asset
- 05WebGPU / WASM
Local inference backend
- 06Score badge
Uncalibrated model output
START WITH ONE EMAIL
Need something
like this?
Tell us what you would use it for. The four lines on the right are enough to start.
There is no form to fill in and nothing to sign up for.
WHAT TO PUT IN IT
- The taskWhat is done by hand today, and how often.
- The toolsWhere the data lives: files, sheets, apps.
- The resultWhat a good outcome looks like for you.
- The timingWhen you need it.
The button opens your email app with the four questions already in the message. Examples: how to write a software brief.