# Autonom documentation

Canonical URL: https://autonom.yatsuk.me/docs/

Let your agent drive an iOS Simulator or an Android emulator, and bring back proof of what it saw.

- [Your first check](https://autonom.yatsuk.me/docs/first-check/index.md)
- [Install](https://autonom.yatsuk.me/docs/install/index.md)
- [Error codes](https://autonom.yatsuk.me/docs/safety/index.md#codes)

## Quick start

Four steps in a terminal, then your agent takes over.

1. **Get the code.** Clone the repository and step into it.

   ```sh
   git clone https://github.com/aiatsuk/autonom
   cd autonom
   ```

2. **Install it.** A checklist asks which device tools to add. Tick your agents too, and each one gets the skills.

   ```sh
   ./install.sh
   ```

3. **Ask what this machine can do.** Green means installed, not proven. Anything missing comes with the exact fix.

   ```sh
   autonom doctor
   ```

4. **Take the tour.** Start a new agent session so it loads the skills. Then take the guided walk on your device.

   ```sh
   autonom tour
   ```

[Your first check](https://autonom.yatsuk.me/docs/first-check/index.md)

## Topics

Six groups, in the order you are likely to need them.

### 1. Start

Install Autonom, run a first check and learn how your agent owns a device.

- [New to Autonom? Start with your first check](https://autonom.yatsuk.me/docs/first-check/index.md): Point your agent at a Simulator or emulator and get back screenshots and a journal. (Start here)
- [Install](https://autonom.yatsuk.me/docs/install/index.md): Put the command line on your PATH and give your agent the skills.
- [Sessions and targets](https://autonom.yatsuk.me/docs/sessions/index.md): Own one device at a time and read every step back.
- [Skills and routing](https://autonom.yatsuk.me/docs/skills/index.md): See which skills your agent loads for Flutter, native Android or iOS.

### 2. Drive

Read the screen and act on it by what each element says.

- [Read and drive the screen](https://autonom.yatsuk.me/docs/screen/index.md): Find, tap, type and swipe by label.
- [Device state](https://autonom.yatsuk.me/docs/device-state/index.md): Open deep links, set permissions and location.

### 3. Observe

Keep what proves a change, see what the app sent, and hand a run to your agent.

- [Evidence](https://autonom.yatsuk.me/docs/evidence/index.md): Take screenshots, recordings, logs and crash reports.
- [Network](https://autonom.yatsuk.me/docs/network/index.md): Capture and mock requests, only with your consent.
- [Report bundle](https://autonom.yatsuk.me/docs/report-bundle/index.md): Keep a run as one verified directory that outlives the session.
- [Agent report](https://autonom.yatsuk.me/docs/agent-report/index.md): Read a run as compact JSON your agent can act on.

### 4. Automate

Save a check once, run it in CI on every change, and pre-test a ticket before QA.

- [Flows](https://autonom.yatsuk.me/docs/flows/index.md): Write a check as a YAML file and run it again.
- [App memory](https://autonom.yatsuk.me/docs/memory/index.md): Keep notes and runbooks for each app.
- [Ticket pre-test](https://autonom.yatsuk.me/docs/pretest/index.md): Check one ticket and its diff on a device, and hand QA a verified pack.
- [Replay](https://autonom.yatsuk.me/docs/replay/index.md): Rebuild the state of a recorded run at the step you choose.
- [CI campaigns](https://autonom.yatsuk.me/docs/ci/index.md): Run flows as one gated campaign, across runners, with exit codes.

### 5. Go further

Measure the app, and watch the device in your browser.

- [Performance and memory](https://autonom.yatsuk.me/docs/performance/index.md): Measure memory, CPU, frames and traces.
- [Mobile Canvas](https://autonom.yatsuk.me/docs/canvas/index.md): Watch and drive one device or several in your browser.

### 6. Reference

Look up an error code, what consent covers, and what a target can do.

- [Safety and errors](https://autonom.yatsuk.me/docs/safety/index.md): Branch on a stable error code, with a hint and exit code 2.
- [Capabilities](https://autonom.yatsuk.me/docs/capabilities/index.md): Ask a target what works there before your agent relies on it.

## How Autonom works

- **Skills and one command line.** Your agent loads skills that say what to do, and runs `autonom`, a command line that answers in JSON. No MCP server is needed.
- **One explicit target.** A session owns one device. With more than one ready, your agent names the one it means, or gets an error listing the candidates.
- **The evidence ladder.** Each rung is stronger evidence, from code and tests to the screen, logs, performance and a before and after replay. Your agent climbs as far as the claim needs.

*Diagram: Five boxes in a row joined by arrows: your agent, skills, the autonom command line, one target and evidence.*

Your agent follows the skills and runs one command line against one target.