Skip to content
MustHave.ai Musthave.ai

Midscene.js

Write end-to-end UI tests in natural language and inspect the steps in replayable reports.

Be the first to review0 followers2 listing views

About this product

Midscene.js uses a configured AI model to interpret what is visible in an interface and carry out test steps. You can describe actions and expected results in YAML or call the agent from JavaScript. The web documentation covers Playwright, Puppeteer, and a Chrome extension. The project also documents other runtimes, including mobile devices.

Start with a staging workflow that has a result you can check independently, such as applying a filter and verifying the resulting item count. Run it several times with the same browser viewport. Open the HTML report and look at any steps the agent had to retry. If the test protects a critical path, use a fixed assertion on the final state so a plausible-looking screenshot does not count as success by itself.

The repository uses the MIT license. Model setup and charges depend on the provider you configure.

Features

  • Natural-language UI actions
  • Playwright and Puppeteer integration
  • Web and mobile automation
  • HTML reports with step screenshots

Launches and product updates

Product announcements submitted for editorial review before publication.

No launch updates have been published here yet.

Experiences from people who have used the product. Reviews are moderated before publication.

Share what worked for you

No community reviews yet. Your experience can help someone choose the right tool.

Review this product

Sign in to rate this product and share your experience.

Sign in to review

Ask a question, share a workflow or talk with the product team. Messages are moderated before they appear.

No discussions yet. What would you like to know about this product?

Join the conversation

Explore similar tools

Other products in these categories. Compare their features and pricing for your task.

Seldon Wren

Run browser QA from plain-language scenarios and inspect the evidence for each failure.

AI Code TestingTen free completed runs per workspace, then $3 per completed run

TestSprite

Describe how your app should behave and use an AI testing agent to build, run and revisit end-to-end checks.

AI Code TestingFree plan: 150 credits/month, one environment and 30 days of run history. Monthly Starter is advertised at US$0 for the first month, then US$19/month for 400 credits. Other plans and annual commitments have different limits.

Product team

The product team has not claimed this listing yet.

Claim this startup

Are you the maker or an authorized team member? Request access to manage this listing. Ownership is checked before access is granted. If approved, your account display name will appear publicly as the verified listing manager. Your verification evidence stays private.

Claiming an existing listing is free. Your listing credits and your free first new listing stay available for new submissions.

Add a badge to your website

Link visitors to this profile with a live MustHave badge.

Add a MustHave badge

Show your MustHave listing on your website. The badge displays its current community vote count.

Light badge

Midscene.js on MustHave.ai

Dark badge

Midscene.js on MustHave.ai