Claude Code multi-agent

Mobile Agent Testers

20 AI testers on 20 different phones, in parallel, for $0: Claude Code agents on iOS Simulators and Android emulators via GitHub Actions

28 stars 2 forksMulti-agent & worktrees Plugin marketplace Source

Install

Inside Claude Code
/plugin marketplace add pierridotite/mobile-agent-testers

Found in the project README. Check it for setup steps after installing.

From source
git clone https://github.com/pierridotite/mobile-agent-testers.git

From the README

mobile-agent-testers

20 AI testers on 20 different phones, in parallel, for $0.

Each tester is a Claude Code agent with its own iOS Simulator or Android
emulator on GitHub Actions. It plays a persona, uses your app like a new user
and writes a bug report with screenshots. Flutter, React Native, Expo, native
Kotlin and Swift, Kotlin Multiplatform, Capacitor and .NET MAUI.

Quick start

The demo app has 11 deliberate bugs. On the recorded run above, the 4 demo testers found 9 of them (2 to 7 minutes per agent, about 21 minutes for the whole run, builds included), plus real issues nobody planted (a button under the Android nav bar, no data kept after a relaunch). Model usage: $0.87 for the 4.

Or let Claude set it up for your app:

Test your own app

Supported out of the box (detected automatically):

Agents read the screen from screenshots and the accessibility tree, so any UI
toolkit works. Labelled widgets (Flutter Semantics, contentDescription,
accessibilityLabel) give them more precise tap targets.

How it works

- Personas set the device: model, OS, font size, dark mode, language, location.
- Three tools per agent: see the screen (with tap coordinates), gestures, typing.
- Encrypted results: public repo logs are public, so everything is encrypted with your key.
- Analytics blocked inside the phones, so tests never touch your real stats.

Limits

- GitHub runners are free for public repos: about 20 jobs at once, 5 on macOS.
- 20 agents can use a Claude subscription's 5-hour window in ~15 min: run batches of 6-10.
- Hosted runners are meant for the repo's own project. For a closed-source app, run the workflow in your private repo or on your own Mac.

Star history

Credits

Claude Code ·
AXe ·
android-emulator-runner

Made by @pierridotite (LinkedIn) · MIT license
Read the full README on GitHub

Details

Language
Shell
License
MIT
Last updated
17 November 2026
Topics
ai-agentsandroid-emulatorclaude-codegithub-actionsios-simulatormobile-testingqa

FAQ

What is Mobile Agent Testers?

20 AI testers on 20 different phones, in parallel, for $0: Claude Code agents on iOS Simulators and Android emulators via GitHub Actions It is a multi-agent for Claude Code, from pierridotite/mobile-agent-testers on GitHub.

How do I install Mobile Agent Testers?

Run /plugin marketplace add pierridotite/mobile-agent-testers inside Claude Code, then follow the setup in the README.

Is Mobile Agent Testers popular?

pierridotite/mobile-agent-testers has 28 GitHub stars and 2 forks. It was last updated on 17 November 2026.

More multi-agent & worktrees

Browse the most popular Claude Code mods, all multi-agent & worktrees, or the skills and MCP server directories.