Add Midscene to your Playwright or Puppeteer tests, or drive your own Chrome via Bridge Mode.
Test and automate desktop apps on macOS, Windows, and Linux with natural language.
Test and automate Android, iOS, and HarmonyOS apps on real devices and simulators.
Automate any interface you can screenshot — beyond DOM and accessibility limits.
Strong visual grounding for reliable element location — a solid default for Midscene.
Supports DeepSeek, Qwen, GPT, Gemini, Kimi, and more.
Doubao Seed 2.1 Turbo: $0.59 total API cost for 60 AppControlBench tasks, with 58 passed.
Pair a planning model with a vision model to raise task completion rates.
Auto-planning for whole flows, plus atomic APIs like aiTap and aiAssert for precise tests.
Drop-in Skills let AI coding agents test your UI through Midscene CLIs.
Replay every step in a visual report, and try ideas fast in the playground.
Write tests in YAML with Midscene Test and extend them with custom TypeScript Nodes.