BREAKING
Windows-Use drives GUI via LLMs
How Windows-Use reads the screen
1
Read UIA tree
↓
2
LLM decides
↓
3
Click / type / scroll
UIA vs vision-based agents
Windows-Use
UIA tree
●
No computer vision
●
Resilient to layout shifts
●
use_vision=False default
Computer Use
vision
●
Reads screenshots
●
Unstable at high-DPI
●
Font differences hurt it
0
M+
Windows-MCP users
0
s
min latency
0
s
max latency
MIT license, Windows 7 to 11
Run it in a sandbox
AI NEWS BLITZ
An open-source AI agent now controls Windows using large language models, no computer vision needed.