KI direkt im Browser: Vektorsuche in Chrome-Extension unter Manifest V3
Ein Entwickler zeigt, wie Bildmerkmal-Extraktion und Vektor-Ähnlichkeitssuche komplett clientseitig in einer Chrome-Extension laufen. Dabei verlässt kein Bild das Gerät des Nutzers, trotz der Einschränkungen durch Manifest V3. Das Beispielprojekt trägt den Namen OmniPic.
This is an engineering write-up, not a product launch. It documents how I run image feature extraction and vector similarity search entirely on the client side of a Chrome extension — no image ever leaves the user's device — under the constraints Manifest V3 imposes. The working example is OmniPic, one of the extensions in the OmniSuite collection ( https://omnisuite.top ).
Takeaway: on-device AI is not "move the server code into the page." The architecture has to be rebuilt around short, recoverable, lazily loaded work.
Image -> on-device feature extraction -> 1024-d vector -> local index Query image -> same extraction -> cosine similarity -> TopK -> results Enter fullscreen mode Exit fullscreen mode Decisions worth noting:
You can verify the privacy property yourself: open DevTools' Network panel while the tool runs — image content should never appear in an outbound request.
The image a page displays is usually a CDN-resized version. Getting the original means:
No clever trick here — just patient handling of how real sites structure their markup.
The same on-device foundation powers the rest of the collection I maintain:
The value of on-device AI is not just speed or saving server costs — it is data ownership. A user's photos, resume, and drafts should not have to be uploaded to make a small feature work. If you are building extensions, I would genuinely like to compare notes in the comments. The tools mentioned are on the Chrome Web Store (OmniPic, ResumeRadar, OmniGame) and the project site is omnisuite.top.