Ui.Vision

Name: Ui.Vision
Rating: 3.91 (239 reviews)
Author: Ui.Vision / a9t9 software GmbH

Task and UI test automation with Computer Vision/OCR. Ui.Vision combines browser automation and desktop automation.

As of June 2026, Ui.Vision has 200,000 users and a 3.91/5 rating from 239 reviews in the Developer Tools category.

Ui.Vision / a9t9 software GmbH Developer Tools★ Featured

Chrome Web Store ↗.crx

Users+100.0%

200.0K

200,000

Rating0%

3.91

239 reviews

Reviews0%

239

Version

9.6.0

Manifest V3

90-day change · In the last 90 days this extension gained 100.0K users, 1 version update.

History

4 snapshots

Tracking since Apr 1, 2026.

View as table

Date	Users	Rating	Reviews	Version
Apr 1, 2026	100.0K	3.91	239	9.5.9
Apr 19, 2026	100.0K	3.91	240	9.5.9
May 10, 2026	200.0K	3.91	239	9.5.9
Jun 20, 2026	200.0K	3.90	238	9.6.0
Now	200.0K	3.91	239	9.6.0

Permissions & access

Permissions: bookmarksclipboardReadclipboardWritecookiesdebuggerdownloadsdownloads.uinotificationsstoragetabsactiveTabproxynativeMessagingcontextMenuswebRequestwebRequestAuthProvidersidePanelscripting
Host access: <all_urls>

Screenshots

About

Ui.Vision is an open-source automation RPA software that combines classic browser automation with modern computer vision and OCR:

(1) Browser Automation

Ui.Vision's computer vision commands make automating tasks inside the web browser easy. Existing Selenium IDE scripts can be imported. Conversion help for iMacros scripts is provided, too.

(2) Desktop Automation for Windows, Mac, and Linux

Beyond web browser automation, Ui.Vision can interpret images and text on the desktop, executing actions like clicking, moving, dragging and dropping the mouse, and simulating keyboard inputs.

This desktop automation requires installing the free Ui.Vision XModules, available for Windows, Mac, and Linux. These modules provide Ui.Vision with the necessary capabilities for desktop interaction.

(3) Anthropic Claude Computer Use Integration

The AI commands allow you to automate complex tasks with a single line of code that would traditionally require hundreds of lines of classic commands. For example, you can teach Ui.Vision to play TicTacToe with just one short "Play this game..." prompt.

(4) Command Line API

Ui.Vision can be controlled from the command line. Thus it can be used from, and combined with, any programming or scripting language, such as Windows batch files, Linux/Mac shell scripts, Python or PowerShell.

(5) Open-Source

Ui.Vision is Open-Source. The source code is available on Github.

(6) 100% Local Software

The software does not send any data back to us or any other place. Everything, including image recognition and OCR processing, is done locally on your machine.

The only exception to the "all data is processed locally" rule is if you select the optional AI commands. But these cloud-features are disabled by default. The default computer vision (image recognition and OCR) runs 100% locally on the machine.

**Happy Automating!**

For questions and suggestions, please visit the Ui.Vision community forum at https://forum.ui.vision.