Privacy and advertising choices

Git-Stars uses essential storage for site operation. Optional analytics and ad-measurement scripts stay disabled unless you accept them; partners such as Google may then use cookies or similar identifiers where required. Privacy Policy

LogoGit-Stars
Top StarsTrendingAI AgentsDaily PicksViral ReposInsights
LogoGit-Stars

Discover top GitHub projects with real rankings and AI insights

GitHub
Built withLogo of Git-StarsGit-Stars
Rankings
  • Top Stars
  • Trending
  • AI Agents
  • Daily Picks
  • Explore
Resources
  • Insights
  • Editorial Policy
About
  • About
  • Contact
Legal
  • Privacy Policy
  • Terms of Service
© 2026 Git-Stars. All Rights Reserved.
MI

web-infra-dev/midscene

AI Agent

AI-powered, vision-driven UI automation for every platform.

15k Stars1.1k Forks90 Open Issues15k WatchersTypeScriptMIT
Developer ToolAutomationUI FrameworkInfrastructure
Review Readiness

This repository page has enough original analysis, source evidence, and comparison context to be treated as an indexable Git-Stars review.

100

review score

Indexable review
Decision Snapshot

Problem solved

Traditional UI automation and AI tools that parse the DOM or accessibility tree fail on dynamic or non-semantic elements (icon-only buttons, canvas, native apps, cross-origin iframes) and break with UI refactors. Midscene solves this by operating purely on screenshots, so it works on any platform and any visible element, and can assert visual states (colors, layout) rather than just DOM existence.

Deployment reality

The available setup signal starts with: npm install @midscene/web. Treat this as a starting point, then ask Codex or Claude to inspect the README, environment variables, runtime version, and deployment target before production use.

Commercial use

The recorded license is MIT. This is a useful commercial-use signal, but teams should still verify license text, dependencies, model/API terms, and trademark constraints.

Capability ceiling

Developers can build end-to-end UI tests, automated workflows, and AI-agent-driven automation for web, Android, iOS, HarmonyOS, desktop apps, and custom interfaces using a unified JavaScript SDK or YAML. Use cases include form validation, mobile app interactions (e.g., ordering coffee, liking tweets), data extraction, and even robotic arm control for in-vehicle testing. The ceiling is limited only by what a human can see on screen, with integration into Playwright/Vitest and AI agents via Midscene Skills.

Source and compliance noteLast synced: Aug 13, 2026

Git-Stars is independent and not affiliated with GitHub or this project. Analysis may be AI-assisted and based on public repository metadata plus short README-derived summaries. We do not mirror full README files, docs, issues, or social comments.

Original GitHub sourceMethodologyEditorial Policy
Editorial Evaluation

web-infra-dev/midscene is tracked as a TypeScript project in the Developer Tool, Automation, UI Framework, Infrastructure area. This evaluation combines public GitHub metadata, category signals, short source summaries, and Git-Stars editorial rules rather than copying project documentation.

Momentum check: the repository has 15k total stars, with +11 today, +0 this week, and +0 this month. These growth windows help distinguish durable adoption from short-lived visibility spikes.

Maintenance check: current activity is Active; the latest push was 11 days ago, and the open issue queue is 90, about 0.62% of total stars. Treat this as an adoption signal, not a substitute for engineering due diligence.

Adoption check: 1.1k forks and 15k watchers suggest how often the project is reused or followed. License signal: MIT. Always verify license compatibility before commercial or internal use.

Practical fit: this project is most relevant when you need AI prototypes, LLM workflows, and agent-style applications. Be cautious when you need a legal review, security audit, or production SLA.

Source check: Git-Stars currently has 2 explicit source reference(s) for this report and a recent growth signal of 11. Follow the original GitHub repository for final install, security, and release information.

Evidence Checklist

Analysis

Ready

Original problem, capability, and verdict guidance are available.

Sources

Ready

Repository metadata and README/source references are attached.

License

Ready

MIT is recorded for review.

Maintenance

Ready

Recent activity is visible in repository metadata.

Alternatives

Ready

Enough nearby projects exist for comparison.

Best For
  • AI prototypes, LLM workflows, and agent-style applications
  • TypeScript teams evaluating ecosystem-native tooling
  • teams that prefer mature projects with broad adoption signals
  • use cases where recent maintenance matters
Avoid When
  • you need a legal review, security audit, or production SLA
Adoption Signals

Momentum

15k Stars

Reuse

1.1k Forks

Attention

15k Watchers

Maintenance

active

License

MIT

Open issues

90

Overview

Midscene.js is an open-source, vision-driven UI testing and automation tool that lets you write tests in natural language and automate any platform, including web browsers, Android, iOS, HarmonyOS, and desktop apps. It works from screenshots alone, eliminating the need for fragile selectors and enabling interaction with any visible element, even those without semantic markup. It integrates with Playwright, Vitest, and AI agents via Skills.

Key Features

- Natural language test writing with vision-driven AI (no selectors needed) - Works on any platform: web, Android, iOS, HarmonyOS, desktop, and custom interfaces - Supports visual assertions (colors, layout, rendered state) and integrates with Playwright/Vitest or AI agents via Skills

Tool Positioning

Developer Tool

Tools that improve coding, testing, build, and local workflow

Automation

Workflow automation, integration glue, and orchestration

UI Framework

Frontend frameworks, design systems, and interface libraries

Infrastructure

Cloud, deployment, networking, containers, and platform tooling

Quick Start
npm install @midscene/web
View on GitHub Project Homepage
Project Activity

80

Health Score

Active

Commit Activity

Jul 23, 2024

Created

Aug 12, 2026

Last push

Source Trail

GitHub repository metadata

metadata

GitHub README

readme_summary

Star History

+0

Today's growth

+0

7-day growth

+0

30-day growth

Aug 13, 2026Aug 13, 2026
Community Health
1.1k

Forks

90

Open

15k

Watchers

Owner
MI

web-infra-dev

GitHub profile
Topics & Language
TypeScriptaiai-testbrowser-usecomputer-usegpt-operatorjavascriptphone-usetesting
Ecosystem & Usage
GitHub Repository Project Website Search on npm
Alternatives & Comparison

codecrafters-io/build-your-own-x

Master programming by recreating your favorite technologies from scratch.

540k

sindresorhus/awesome

😎 Awesome lists about all kinds of interesting topics

496k

freeCodeCamp/freeCodeCamp

freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming, and computer science for free.

454k

EbookFoundation/free-programming-books

:books: Freely available programming books

394k

nilbuild/developer-roadmap

Interactive roadmaps, guides and other educational content to help developers grow in their careers.

365k
License
MIT
CreatedJul 23, 2024
Last pushAug 12, 2026
Last syncedAug 13, 2026
Repository Standards

✓

License

✓

Forked

✓ Active

Maintained

AI AnalysisAnalyzed by Git-Stars

Problem Solved

Traditional UI automation and AI tools that parse the DOM or accessibility tree fail on dynamic or non-semantic elements (icon-only buttons, canvas, native apps, cross-origin iframes) and break with UI refactors. Midscene solves this by operating purely on screenshots, so it works on any platform and any visible element, and can assert visual states (colors, layout) rather than just DOM existence.

Capabilities

Developers can build end-to-end UI tests, automated workflows, and AI-agent-driven automation for web, Android, iOS, HarmonyOS, desktop apps, and custom interfaces using a unified JavaScript SDK or YAML. Use cases include form validation, mobile app interactions (e.g., ordering coffee, liking tweets), data extraction, and even robotic arm control for in-vehicle testing. The ceiling is limited only by what a human can see on screen, with integration into Playwright/Vitest and AI agents via Midscene Skills.

Bottom Line

Midscene.js is ideal for QA engineers and developers who need robust, cross-platform UI automation that survives UI changes and works on non-semantic elements. It should be avoided by those requiring deterministic, structure-based automation or who lack access to AI models. The key trade-off is trading selector reliability for AI-driven visual understanding, which offers flexibility but introduces model-dependent variability.

Full AI Analysis