Ui.Vision RPA is an open-source Robotic Process Automation tool designed for automating web and desktop tasks. It targets individual users and businesses seeking to automate repetitive processes, offering features like computer vision, OCR, and LLM integration, alongside Selenium IDE compatibility.

How It Works

Ui.Vision functions as a browser extension, enabling it to interact with web pages and applications. It leverages a combination of JavaScript for browser automation, computer vision for visual recognition of UI elements, and OCR for text extraction. The integration with LLMs and Anthropic's models suggests advanced capabilities for understanding and interacting with content contextually.

Quick Start & Requirements

• Install via Chrome, Firefox, or Edge web stores.
• For development: Node.js v20.11.1, npm v10.2.4.
• Build commands: npm i -f, npm run build, npm run build-ff, npm run ext.
• Official Homepage: https://ui.vision/

Highlighted Details

• Cross-platform support for macOS, Linux, and Windows.
• Includes Selenium IDE import/export functionality.
• Features computer vision and OCR capabilities.
• Integrates with LLMs, including Anthropic.

Maintenance & Community

• User forum for questions and support.
• Contact: TEAM AT UI.VISION

Licensing & Compatibility

• Free for private and commercial purposes.

Limitations & Caveats

• Building the extension is only necessary for developers; end-users should install from web stores.