# midscene

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

## Facts
- **Category:** [Browser & Computer Use](https://agentsearchengine.app/category/browser-agents)
- **Type:** Agent
- **Pricing:** Open source
- **GitHub stars:** 14,469
- **Language:** TypeScript
- **License:** MIT
- **Last repo activity:** today (Aug 3, 2026)
- **Official site:** https://midscenejs.com
- **Source code:** https://github.com/web-infra-dev/midscene
- **Listing on Agent Search Engine:** https://agentsearchengine.app/agents/midscene
- **Data verified:** July 2026

## Best for
Writing UI tests in natural language across web, iOS, and Android.

## About midscene
Open-source, vision-driven UI testing — write tests in natural language, automate any platform. Most UI automation — including AI tools that read the DOM or the accessibility tree — depends on page structure. That structure is fragile and incomplete: selectors break on every refactor, elements without semantic markup (icon-only buttons, custom controls, ) are invisible to it, native apps and cross-origin iframes are out of reach, and it cannot tell whether something actually looks right. Midscene works from the screenshot alone, and you describe each step in natural language: Midscene is built for UI testing first, but the same vision-driven engine handles any UI automation task.

_From the project's README._

## Alternatives
midscene sits in browser & computer use. Related tools indexed here:
- [UI-TARS-desktop](https://agentsearchengine.app/agents/ui-tars-desktop) — The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra · Open source · Agent · 38k★ · TypeScript · Apache-2.0 · active 1 day ago
- [page-agent](https://agentsearchengine.app/agents/page-agent) — JavaScript in-page GUI agent. Control web interfaces with natural language. · Open source · Agent · 28k★ · TypeScript · MIT · active 7 days ago
- [skyvern](https://agentsearchengine.app/agents/skyvern) — Automate browser based workflows with AI · Open source · Agent · 23k★ · Python · AGPL-3.0 · active today
- [nanobrowser](https://agentsearchengine.app/agents/nanobrowser) — Open-Source Chrome extension for AI-powered web automation. Run multi-agent workflows using your own LLM API key. Alternative to OpenAI Operator. · Open source · Agent · 14k★ · TypeScript · Apache-2.0 · active 8 months ago
- [Agent-S](https://agentsearchengine.app/agents/agent-s) — Agent S: an open agentic framework that uses computers like a human · Open source · Framework · 12k★ · Python · Apache-2.0 · active 2 days ago
- [robotgo](https://agentsearchengine.app/agents/robotgo) — RobotGo, Go Native cross-platform RPA, GUI automation, Auto test and Computer use @vcaesar · Open source · SDK / library · 11k★ · Go · Apache-2.0 · active 5 days ago
- [llm-scraper](https://agentsearchengine.app/agents/llm-scraper) — Turn any webpage into structured data using LLMs · Open source · SDK / library · 6.9k★ · TypeScript · MIT · active 1 day ago
- [fara](https://agentsearchengine.app/agents/fara) — Fara-7B: An Efficient Agentic Model for Computer Use · Open source · Agent · 6.1k★ · Python · MIT · active 12 days ago

---
Source: [Agent Search Engine](https://agentsearchengine.app) — an independent, hand-curated index of AI agents, MCP servers, and frameworks. Rankings are never sold; sponsored placements are labeled and never numbered. Full directory: https://agentsearchengine.app/llms-full.txt