claudeers.
// Automation & Workflows

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

Install with your AI

Paste into Claude Code, Cursor, or any agent — it reads the repo and wires the tool into your project.

Install and set up mobile-agent-testers (git-clone project) into my current project.
Found on https://claudeers.com/mobile-agent-testers
Repo: https://github.com/pierridotite/mobile-agent-testers
Homepage/docs: —
Detected install method: git-clone → git clone https://github.com/pierridotite/mobile-agent-testers
Category: automation. Platforms: api, web, mobile.
Read the repo's README for exact setup and env vars, then install it and wire it into my project.

Claudeers Health Verdict:
unknown; community-verified: false. Confirm the source before running anything.
// or clone
git clone https://github.com/pierridotite/mobile-agent-testers

// compatibility

Platformsapi, web, mobile
Operating systems—
AI compatibilityclaude
LicenseMIT
Pricingopen-source
LanguageShell

Get your FREE $2.50 API credits to access TickAtlas financial data ↗

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.

Real screen recordings of four AI testers using the demo app at the same time (small Android phone, Pixel 7 in dark mode, iPhone SE in French, iPad with the largest text), with each bug they find shown under its phone

Quick start

gh repo create my-testers --public --template pierridotite/mobile-agent-testers --clone
cd my-testers && ./setup.sh           # key pair + secrets + Claude token (Windows: .\setup.ps1)
gh workflow run agent-testers.yml     # demo: 2 Android + 2 iOS testers, ~20 min
bash scripts/collect.sh <run id>      # decrypts reports into runs/<id>/SUMMARY.md

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:

/plugin marketplace add pierridotite/mobile-agent-testers
/plugin install mobile-agent-testers@mobile-agent-testers

Test your own app

gh workflow run agent-testers.yml -f source_repo=you/app -f app_id=com.you.app \
  -f android_personas=anna,malik -f ios_personas=clara,jonas
Input
source_repo, refApp repo and branch (empty = this repo). Private repo: add a read-only SOURCE_REPO_TOKEN secret
app_dir, app_idApp folder, Android package / iOS bundle id (if the other platform uses another id, it is read from its built app)
android_personas, ios_personasIds from personas.json, one phone each
briefAgent instructions (AGENT_BRIEF.md)
frameworkauto (default) or force one of the frameworks below
android_build + apk_path, ios_build + ios_app_pathYour own build command, or a download of a prebuilt app (paths relative to app_dir)
block_hostsAnalytics hosts blocked during tests
record_videoScreen recording of each phone, encrypted with the reports

Supported out of the box (detected automatically):

FrameworkAndroidiOS Simulator
Flutterflutter build apkflutter build ios --simulator
React Native / ExpoGradle releaseXcode, arm64
Native Kotlin / Java, Swift / Objective-CGradle debugXcode, arm64
Kotlin MultiplatformGradle debugXcode project of the iOS app
Capacitor / IonicGradle debug after cap syncXcode after cap sync
.NET MAUI (beta)dotnet publishdotnet build for iossimulator-arm64
Anything elseandroid_build + apk_pathios_build + ios_app_path

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

How it works: one workflow builds the app, then one emulator or simulator with one agent per persona, encrypted reports, summary on your machine

  • 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

Star History Chart

Credits

Claude Code · AXe · android-emulator-runner

Made by @pierridotite (LinkedIn) · MIT license

// 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 open-source on GitHub.

Is mobile-agent-testers free to use?

mobile-agent-testers is open-source under the MIT license, so it is free to use.

What category does mobile-agent-testers belong to?

mobile-agent-testers is listed under automation in the Claudeers registry of Claude-compatible tools.

1 views
★ 32 stars
unclaimed
updated about 22 hours ago

// embed badge

mobile-agent-testers on Claudeers
[![Claudeers](https://claudeers.com/api/badge/mobile-agent-testers.svg)](https://claudeers.com/mobile-agent-testers)

// retro hit counter

mobile-agent-testers hit counter
[![Hits](https://claudeers.com/api/counter/mobile-agent-testers.svg)](https://claudeers.com/mobile-agent-testers)

// reviews

// guestbook

0/500

// related in Automation & Workflows

🔓

The agent that grows with you

// automationNousResearch/⟨Python⟩★ 260,254◷ MIT[ claude ]
🔓

The API to search, scrape, and interact with the web at scale. 🔥

// automationfirecrawl/⟨TypeScript⟩★ 199,533◷ AGPL-3.0[ claude ]
🔓

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

// automationbrowser-use/⟨Python⟩★ 121,235◷ MIT[ claude ]
🔓

Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop

// automationLeonxlnx/⟨JavaScript⟩★ 110,676◷ MIT[ claude ]
→ see how mobile-agent-testers connects across the ecosystem