Enables an AI agent to see and control a Linux desktop via Wayland/Hyprland, providing screenshots, structured desktop state, pointer/keyboard input, semantic window/workspace tools, and a policy engine for safe execution.
Gives AI assistants eyes and hands on your desktop, letting them view and capture the screen, click, type, use the clipboard, run shell commands, and execute multi-step tasks with a single per-task authorization while keeping context small via a local state file.