Midscene.js
Vision-driven UI automation and E2E testing framework where a GUI agent carries out natural-language steps on web, mobile and desktop apps.
Updated
✨ Try AgentScout's free AI image generator →Good for: browsing the web, controlling a computer, automating workflows, building AI agents, testing apps
Use cases
About Midscene.js
Midscene.js is listed in our browser/computer use category and is aimed at builders. Vision-driven UI automation and E2E testing framework where a GUI agent carries out natural-language steps on web, mobile and desktop apps. Pricing, as the maker states it: Open source. Maturity: Mature. We last checked the official link on 2026-10-18.
What is Midscene.js?
Midscene.js brings AI vision to end-to-end testing for web, mobile and desktop apps. You describe UI steps and expected results in natural language, and its visual GUI agent carries them out and checks what users see.
You can write YAML test cases with Midscene Test or call its agent APIs from existing Playwright tests, and review HTML reports with screenshots, actions and assertion results.
Sources: the official README and our directory listing, checked 2026-10-18. Official site: midscenejs.com/introduction.
Who is Midscene.js for?
QA engineers and developers who want to write end-to-end tests in plain language instead of brittle selectors.
Midscene.js at a glance
- Open source: Yes (MIT License)
- GitHub: web-infra-dev/midscene · 15,351 stars (as of Oct 21, 2026)
Key features
- Natural-language E2E tests
- Visual GUI agent for web, mobile and desktop
- YAML test cases with Midscene Test
- Integrates with Playwright
- HTML reports with screenshots and assertions
Midscene.js FAQ
What is Midscene.js?
Midscene.js brings AI vision to end-to-end testing for web, mobile and desktop apps. You describe UI steps and expected results in natural language, and its visual GUI agent carries them out and checks what users see.
Who is Midscene.js for?
QA engineers and developers who want to write end-to-end tests in plain language instead of brittle selectors.
Is Midscene.js free?
Midscene.js's pricing, as the maker states it: Open source. Open-source tools are free to use, though you may still pay for model API usage or a hosted plan. Check the official site for current plans.
Is Midscene.js open source?
Yes. Midscene.js is released under the MIT License, according to its GitHub repository.
What are alternatives to Midscene.js?
Similar tools include Stagehand, Agent Device, TuriX CUA, UFO, Qwen-UI-Agent and Agent-S.
Midscene.js ratings and reviews
Be the first to rate Midscene.js: tap 1 to 5 stars below. A written review is optional.
Midscene.js alternatives
Other browser/computer use tools in our directory. See all browser/computer use tools →
Stagehand
Browser automation framework mixing code with natural-language actions.
Agent Device
Mobile app automation and verification for coding agents on iOS and Android.
TuriX CUA
Computer-use agent that operates desktop apps.
UFO
Microsoft's desktop agent framework that operates Windows apps and orchestrates multi-device tasks as task graphs.
Qwen-UI-Agent
Tongyi foundation GUI agent model that operates mobile, computer and browser interfaces, trained and evaluated on real devices.
Agent-S
Open agentic framework that uses computers like a human through the GUI.
Popular searches with this tool
🏆 Ranked in: UI-TARS-desktop alternatives · Best AI Browser Agents
🔁 Listed in: UI-TARS-desktop alternatives
🧭 Task guides: Mobile and remote control tools for web browsing agents · AI testing and QA tools · Computer and desktop control tools for web browsing agents
Badge for makers
Built Midscene.js? Add this badge to your README or site. It links back to this page. About badges
