Open-source RPA software for browser and desktop automation with OCR and AI integration.
UI.Vision is an open-source robotic process automation (RPA) tool that automates browser and desktop workflows using Selenium-style commands, computer vision, OCR, and AI. It supports Windows, macOS, and Linux, running l
Updated Oct 26, 2026
No written reviews yet. Be the first to share your experience.
Tried this tool? Share your experience.
The assistant inspects the page, writes a macro, runs it and helps fix failures.
Keep the resulting macro to edit and run again.
Connect an MCP-compatible assistant to Ui.Vision. It can inspect the live page, create and edit macros, run them in your browser, and read the logs to help resolve failures. You keep a reusable macro for the next run.
In Ui.Vision V10, Browser Vision on Chrome and Edge works without XModules, even with the browser window in the background.
Choose hosted Ui.Vision AI, your own AI provider, or a local model.
The MCP bridge runs on your computer; data shared with your AI assistant is handled by the provider you choose. Set up the Ui.Vision MCP bridge .
Freemium. Paid plans start at $299 per year.
$0
$299
per year
Record or code it: Build workflows with visual recording, Selenium-style commands , or v10's new JavaScript automation API . Combine browser commands with computer vision and OCR.
No written reviews yet. Be the first to share your experience.
Tried this tool? Share your experience.