Provides agents with temporary visual capture of Hyprland/Wayland monitors, windows, or regions as PNGs, enabling visual verification and self-correction of UI and desktop tasks.
Enables AI assistants to automate Hyprland desktop environments through screenshots, mouse/keyboard input, window management, workspaces, clipboard, app launching, and OCR.
Gives each agent its own isolated nested Hyprland desktop with a private seat, clipboard and accessibility bus, so it can see the screen and drive a mouse, keyboard, touchpad gestures, windows and apps without touching the user's pointer, focus or windows. Exposes screenshots, zoom, OCR, accessibility-tree control, window management and batched actions as MCP tools, and can optionally act read-only, or with input, on the real desktop.
Enables controlling VRoid Studio through desktop GUI automation, letting an MCP client launch the app, capture its window, locate controls via OCR, edit character parameters, and run save/export flows on macOS and Linux/Hyprland.