> ## Content Index
> Fetch the complete content index at: https://techweblearn.com/llms.txt
> Use this file to discover other available public pages before exploring further.

# Google's Open-Source Android Automation Agent
- URL: https://techweblearn.com/googles-open-source-android-automation-agent/
- Published: 2026-09-13T08:20:28.000Z
- Updated: 2026-09-13T09:14:24.000Z
- Author: Kunal

Google's ARTEMIS turns plain-English instructions into reliable Android automation — driving real phones and plugging into Claude Code and Cursor via MCP.  
  
Google just open-sourced something worth your attention: an agent that takes a sentence like *"Open Settings, find Battery, and tell me the current level"* and actually does it on a real Android phone.

It's called **ARTEMIS** — you can grab it at [**github.com/google/artemis**](https://github.com/google/artemis?ref=techweblearn.com) — it's Apache 2.0 licensed, and on Google Research's AndroidWorld benchmark (100+ multi-step tasks across 20+ apps) it reports a **99%+ completion rate**.  
  
Android automation has always meant picking your poison. UiAutomator and Appium are precise but brittle — your test shatters the moment a designer moves a button. Pure computer vision is flexible but slow and unreliable.

ARTEMIS does both. It reads **element indices from the accessibility tree when they exist**, and falls back to **coordinates and vision models** when they don't — Canvas charts, Flutter surfaces, custom Compose layouts. Not either/or. Structure first, vision as backup.

That single design choice is why it holds up on apps that were never built to be testable.

## Two modes: Flash and Pro

**Flash** is the fast path. One model observes the screen, thinks, and acts — roughly **3–5 seconds per step**, token-efficient, no planning overhead. Great for smoke tests and quick "go check this screen" jobs. The tradeoff: no task plan, no safety checks, no final report.

**Pro** is the careful path. A **Planner** writes a living Markdown plan with milestones. An **Operator** executes it with the full toolset. Every single action passes a **Safety Net** before firing. A read-only **Checker** verifies checkpoints and reviews the result against your original goal. Cost: **15–40 seconds per step**.

> Use Flash to *check* something. Use Pro to *prove* something.

Also nice: when an action fails in Pro, it opens an "incident" that stays in the Operator's context until a later action succeeds. Recovery is handled by the agent that already understands the situation — not punted to a separate repair agent that has to relearn everything.

## The feature that'll actually get it adopted

ARTEMIS ships a native **MCP server**.

Translation: Claude Code, Cursor, Codex, Windsurf, VS Code, and Antigravity can drive a real device from inside your editor chat — and read back **Logcat output and screenshots**.

One prompt in your IDE can build the APK, install it, walk the login flow with a test account, watch for unexpected popups, and hand you screenshots of the final screen. That's not a unit test. That's end-to-end verification, triggered conversationally, on the phone already plugged into your machine.

One thing people miss: Google ships a rules file (`mcp_server/rules.md`) with a "mobile testing mindset." Mount it into your IDE's rules. Without it, you're asking a general-purpose assistant to reason about mobile testing with zero domain grounding — and it will confidently hallucinate UI interactions.

## Try it in ten minutes

You need an Android device with USB debugging on, or an emulator. That's it. Clone the repo from [**github.com/google/artemis**](https://github.com/google/artemis?ref=techweblearn.com) and run:

bashCopy

```bash
git clone https://github.com/google/artemis.git && cd artemis
./start.sh
```

(Windows: use `.\start.bat` — PowerShell needs the `.\`.)

The script auto-installs the toolchain — ADB, scrcpy, FFmpeg, uv — then opens a web console at `localhost:8000` with live screen mirroring, a prompt sandbox, and execution replays.

Or skip straight to the CLI:

bashCopy

```bash
uv run artemis run "Open Settings, find Battery and tell me current level" --profile flash
```

There's also a Python SDK for CI pipelines with typed Pydantic outputs, and the client is thin — the models and image processing stay on the device host, so your CI runner just needs network access.

## The honest caveats

The 99% figure is **self-reported** — Google's own repo, Google's own benchmark, Google's own system. It's a strong signal, but AndroidWorld tasks are clean and verifiable in a way your production app's janky onboarding flow is not.

The repo is young, too: roughly **4.1k stars and 119 commits**, well short of Appium's maturity. Pro at 15–40s/step across a long workflow is a coffee break, not a CI gate. And **there's no iOS support** — it's on the roadmap, not in the code.