Mobile testing for AI coding agents
Your agent tests and debugs your app on an iOS Simulator or an Android emulator, and brings back the evidence.
How it works
The same verbs work on an iOS Simulator and an Android emulator. A node has the same shape on both, so one skill drives either platform.
Read the screen as a compact accessibility tree, with a screenshot for proof.
autonom ui tree
Find and tap by what an element says, not by where it sits.
autonom ui tap --desc "Continue"
Every step lands in the session journal with its result and your notes.
autonom journal
Before and after
A tap that returns ok does not prove the screen changed. Your agent compares the tree or the screenshot before and after.
To keep a pair comparable, pin the status bar on both platforms, the keyboard and locale on iOS, and turn animations off on Android. The status bar and keyboard pins fix state the app does not own.
The evidence ladder
Your agent starts at the code and works up to a before and after replay, one rung at a time.
One target
With more than one device ready, your agent names the one it means. Ambiguity is an error listing the candidates.
What it can do
Skills your agent loads and one command line that answers in JSON. No MCP server needed.
UI and accessibility trees, screenshots and recordings, logs and crash reports. Mobile Canvas mirrors and lightly controls the target in your browser. On iOS, frames are polled screenshots.
Commands
Find and tap by label, then swipe, type into the focused field and press keys. ui wait --settled holds until two consecutive trees match.
Watch HTTP and HTTPS traffic through a local proxy and swap in the response you need, fullest on Android. Capture starts only on an explicit flag, and exports to HAR. A screenshot taken during a mock is flagged as mocked.
Save a check as a strict YAML flow and replay it. A mistake is caught at its exact line, and a failed step can suggest close matches from its captured screen. Imports and exports flows within the Maestro Core Profile.
Reports
Your agent keeps notes on each app in ~/.autonom/apps/. A flow approved after consecutive clean replays, three by default, can become an App Skill in your project.
Measure memory, CPU, frames and traces, fullest on Android. Performance skills cover Flutter, native Kotlin and Compose.
Safety
Starting the proxy, attaching a device and installing a CA each take their own flag, every time. Credentials in captured traffic are masked before it is written.
Capture needs --i-understand-mitm on every run, plus a typed phrase on an interactive terminal. No config file, environment variable or earlier grant stands in.
Flow secrets never enter artifacts, and the journal keeps only scrubbed arguments.
It binds 127.0.0.1 with no flag to widen it, and host network settings are never changed.
Sessions live in ~/.autonom/sessions/, outside any repository, so a capture cannot be committed by accident.
Install
Works with Claude Code, Codex, Grok and any agent that loads skills.
Clone the repository and step into it.
git clone https://github.com/aiatsuk/autonom
cd autonom
A checklist asks which device tools to add. Tick your agents too, and each one gets the skills.
./install.sh
Green means installed, not proven. Anything missing comes with the exact fix.
autonom doctor
Start a new agent session so it loads the skills. Then take the guided walk on your device.
autonom tour
Claude Code and Codex can add the skills as a plugin. Start a new session afterwards so it loads.
claude plugin marketplace add aiatsuk/autonom
claude plugin install autonom@autonom
codex plugin marketplace add aiatsuk/autonom
codex plugin add autonom@autonom
Needs git, Python 3.11 and Node 20.11 or later. iOS Simulator targets need a Mac with Xcode. Free under the MIT license.
Point your agent at a Simulator or an emulator and get back a screenshot and a journal of every step.