So recently Anthropic came out with tools that let you drive Windows and Mac OS around. But I don't use Windows or MacOS, and was curious about some Wayland internals stuff and whether it would be possible to build something usable on a relatively restrictive platform like Wayland. So I made Tine.

Tine is a GNOME extension and CLI that lets an agent (I have used Claude but in theory any agent that can access the CLI) drive the desktop around using SPI trees (AT-SPI2), OCR, and visual fallbacks. Agent can do work with the a11y (AT-SPI2) trees, take screenshots, zoom in on a grid, click, enter text using a uinput device, and generally bumble their way around a Wayland Linux desktop.

This project would probably have been way easier in x11 but Wayland is teh future!!!111 Thanks for any thoughts and feedback and feels good to release something here after a decade of lurking. Decade plus but who's counting / I'm not old.