Local AI Overlay
Explain webpage text and images with a model running in LM Studio.
Connect to your local model
Start the LM Studio local server on your PC. The default address is http://127.0.0.1:1234.
The token is saved in this browser's local storage. Use a long, private token before exposing the site through Playit.
Add the overlay to your browser
This is a bookmarklet, not an extension. Enter your access token above first, then drag the updated button below to your bookmarks bar. Click it while viewing any webpage.
Select text on a page. The overlay picks it up automatically. Press Explain.
Open the overlay, choose Pick image, then click an image on the page. You can also upload an image directly.
Continue asking questions in the overlay. The conversation stays open while you browse that page.
LM Studio setup
In LM Studio, load your model, open the Developer / Local Server tab, and start the server on port 1234. Text explanations work with normal chat models. Image explanations require a vision-capable model and the model must be loaded in LM Studio.
For the overlay to work on other sites, the site must allow the embedded frame. Some pages with strict Content Security Policy settings may block it. Image URLs that redirect or require a login may need to be saved and uploaded instead.
Do not expose LM Studio's port 1234 through Playit. Only expose this app's port 8765, and change the access token first.