web-infra-dev/midscene
An AI-powered, vision-driven UI automation framework for every platform, enabling natural language control and scripting.
Core Features
Detailed Introduction
Midscene.js is an innovative, AI-powered UI automation framework designed to simplify interaction with digital interfaces across various platforms. Leveraging vision-driven AI, it allows users to automate tasks by describing goals in natural language or through JavaScript/YAML scripts. It supports web browsers (integrating with Puppeteer/Playwright), mobile applications (Android/iOS), and custom interfaces, offering a robust set of APIs for interaction, data extraction, and utility functions. With features like visual debugging, caching, and a zero-code experience via a Chrome Extension, Midscene.js aims to empower developers and users to create efficient and intelligent automation workflows.