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.

ai-agent automation browser-use computer-use desktop-automation llm mcp mcp-server ollama rpa vision-language-model windows
2 Open Issues Need Help Last updated: Aug 24, 2026

Open Issues Need Help

View All on GitHub
Add drag & drop action about 3 hours ago
enhancement good first issue

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.

Python
#ai-agent#automation#browser-use#computer-use#desktop-automation#llm#mcp#mcp-server#ollama#rpa#vision-language-model#windows
enhancement good first issue

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.

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