#359 · Primary category: AI Agents & Automation

agent-device

adb agentic-ai agents ai-agents android-emulator automation e2e-testing expo flutter ios-simulator mcp mobile mobile-testing performance-optimization react-native testing xcuitest

Mobile app automation and verification for AI coding agents. CLI, MCP server, and typed Node.js API for iOS, Android, HarmonyOS, TV, web, macOS, and Linux.

Project last updated:08/29/26

GitHub Stars

4.3K

Forks

266

Contributors

45

License

MIT

Why we included this project

Most coding agents that touch mobile apps stop at writing code: somebody still has to launch the app and eyeball whether the change took. agent-device closes that gap by letting the agent drive the app itself on real devices, across iOS, Android, and TV. It reads token-efficient accessibility snapshots, finds elements by ref or selector, taps and types, and saves screenshots, video, and logs as evidence a human can review. The inspect-act-verify loop comes from Vercel's agent-browser, and sessions can be replayed, which turns a one-off check into a repeatable regression step. If you'd rather your agent verify its own output than trust its report, this CLI is worth a look.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category