Midscene · House #28,668

What it is

Calls itself “GUI Agent”.

• Calls itself: GUI Agent

“A vision-based GUI Agent for web, mobile, and desktop apps.”

Where it puts itself

Its one line of difference: “Reaches what selectors cannot — unlabeled elements, canvas, native apps, and cross-origin frames”

“Reaches what selectors cannot — unlabeled elements, canvas, native apps, and cross-origin frames”

What it costs

A free tier, free forever. No monthly plan.

• Monthly: no
• Free plan: free forever

“$0.59 Total model API cost for 60 tasks”

“Midscene is free and open source software released under the MIT license.”

Who it sells to

Sells to developers. Available in 2 languages.

• Sells to: developers
• Languages: English · 简体中文

“Add Midscene to your Playwright or Puppeteer tests, or drive your own Chrome via Bridge Mode.”

“English”

How it runs

A command-line tool, desktop app, mobile app and web app for Android, HarmonyOS, Linux, Windows, iOS and macOS. Offers an API. Open source. AI is the core of the product.

• Kind: cli · desktop · mobile · +1
• Runs on: Android · HarmonyOS · Linux · +3
• API: yes
• Open source: yes
• AI role: core to the product

“Drop-in Skills let AI coding agents test your UI through Midscene CLIs.”

“Test and automate with natural language across web, mobile, and desktop”

What it works with

Integrates with Chrome, DeepSeek, Gemini and 2 more. Names Playwright and Puppeteer on its pages.

• Integrates with: Chrome · DeepSeek · Gemini · +2
• Names: Playwright · Puppeteer

“Chrome”

“DeepSeek”

What it offers as proof

Live, no waitlist. Shows customer logos. Claims “15k+”. Backed by ByteDance. Publishes a blog.

• Customer logos: yes
• Number claimed: 15k+
• Backer: ByteDance

“Midscene is free and open source software released under the MIT license.”

“ByteDance Volcengine Douyin TikTok Lark Soda Music Doubao Alibaba Ctrip Xiaomi”