screen-use

active

browser-use, but for the entire desktop — give any AI Agent eyes and hands on Windows. MCP + SDK, VLM-optional, with visual loop, introspection and meta-learning.

Code-only MCP server: no hosted endpoint, so you install and run it yourself. It is not probed, graded or counted in our reachability statistics.

Get it

Repository: github.com/tongriyaotxt/screen-use
License: MIT
Last update: 2026-11-09
GitHub stars: ★ 14

ai-agent automation browser-use computer-use desktop-automation llm mcp mcp-server ollama rpa vision-language-model windows

Listed in

github · source

Run this server as a hosted endpoint? Submit the endpoint and it moves to the remote directory, where it is probed and graded.