Description
Many computer-use approaches rely on vision to read the screen, slow and error-prone. Windows-Use is an AI agent that controls Windows at the GUI layer, reading the screen through the Windows UI Automation API and letting any LLM decide what to click, type, scroll or run.
It needs no computer vision model and works with any LLM.
UI Automation:Real interface elements.
Any model:LLM-agnostic.
No vision:No screenshot parsing.
Desktop actions:Click, type and scroll.
It needs no computer vision model and works with any LLM.
Features
UI Automation:Real interface elements.
Any model:LLM-agnostic.
No vision:No screenshot parsing.
Desktop actions:Click, type and scroll.
