Skip to content

An AI-powered automation SDK can control the page, perform assertions, and extract data in JSON format using natural language.

License

Notifications You must be signed in to change notification settings

web-infra-dev/midscene

Repository files navigation

Midscene.js

Midscene.js

English | 简体中文 | 日本語

Joyful UI Automation

npm version downloads License

Midscene.js is an AI-powered automation SDK can control the page, perform assertions, and extract data in JSON format using natural language.

Midscene.mp4

Features ✨

  • Natural Language Interaction 👆: Describe the steps, and let Midscene plan and control the user interface for you
  • Understand UI, Answer in JSON 🔍: Provide prompts regarding the desired data format, and then receive the expected response in JSON format.
  • Intuitive Assertion 🤔: Make assertions in natural language; it’s all based on AI understanding.
  • Out-of-box LLM 🪓: It is fine to use public multimodal LLMs like GPT-4o. There is no need for any custom training.
  • Visualized Report 🎞️: With our visualized report file, you can easily understand and debug the whole process.
  • Brand New Experience! 🔥: Experience a whole new world of automation development. Enjoy!

Resources 📄

Community

License

Midscene.js is MIT licensed.