claudekit / tools / artemis
[ MCP · Development ]

ARTEMIS

ARTEMIS turns natural-language instructions into reliable Android automation. Its native MCP server lets Claude Code drive real devices and emulators, run test workflows, and collect screenshots and Logcat output, while ARTEMIS's own agent performs the on-device steps in the background.

google/artemis ·updated
$ git clone https://github.com/google/artemis.git && cd artemis && ./start.sh copy

An open source project by Google (google/artemis, Apache-2.0).

Why it matters

When Claude Code changes an Android app, someone still has to tap through a real device to see what the screen does after login, or write and maintain locator-based scripts that break when the layout changes.

ARTEMIS lets AI assistants and test suites use real phones like a human. You describe a task such as “Open Settings, find Battery and tell me current level”, and its agent observes the screen, acts on the device, and returns structured results. Its native Model Context Protocol (MCP) server lets Claude Code hand off that work and collect Logcat output and screenshots.

What you can do with it

Examples from the README:

  • Cross-app automation — the live demo sets up driving routes and calculates total durations in Google Maps, then opens YouTube to play a Coldplay song.
  • Prompt your phone in the IDE chat — the README’s example prompt for Codex, Antigravity, or Claude Code: “Build the latest changes into an APK, install it on the connected device, open the login screen with a test account, verify if there are any unexpected popups after login, and return screenshots of the final page.”
  • Autonomous testing workflow — in the README’s Antigravity example, a test request becomes a step-by-step test plan, autonomous execution on a real device with performance profiling, and a final report with audit findings, metric tables, and raw datasets.
  • Existing test frameworks — the Python SDK integrates into pytest or CI/CD pipelines with typed Pydantic results you can assert on.

The ARTEMIS web console, showing the view switcher, model and replay controls, live agent stream, prompt dock, and task queue

Image source: google/artemis (Apache-2.0)

Key features

  • Five MCP tools

    mobile_run_task launches the job as a detached background process, so the AI agent is not blocked and checks back on the task instead.

    ToolWhat it does
    mobile_run_taskLaunches an autonomous mobile automation task with the Flash or Pro profile
    mobile_manage_taskManages the task lifecycle (status, stop, inject_instruction)
    mobile_get_device_stateReturns a screenshot or OCR+XML hierarchy of the current screen
    mobile_inspect_traceInspects traces with visual action overlays and agent reasoning
    mobile_diagnoseEnvironment doctor that checks Python, LLM credentials, ADB, and devices, and returns an ordered fix list
  • Flash and Pro execution profiles

    Flash is a reactive loop with no task plan, no pre-execution safety net, no checkpoint verification or final report, and no ADB shell. Pro adds a Planner that maintains a Markdown task plan, an Operator whose every single action passes a pre-execution Safety Net (XML-first, pixel fallback), and a read-only Checker that verifies checkpoints and runs a final review against the original goal.

  • Multimodal targeting

    ARTEMIS uses element indices when available, and combines accessibility hierarchies and OCR with visual models for custom Canvas, Compose, and Flutter interfaces.

  • Testing rules for AI assistants

    mcp_server/rules.md, the Mobile Testing Mindset, covers active exploration before coding, Flash vs. Pro routing, latency and timing compensation, the “Dynamic-First, Coordinate-Fallback” locator pattern, and calling mobile_diagnose first whenever a tool errors.

  • Multi-device execution

    Per-device execution locks let distinct devices run in parallel. Omit device_serial to let ARTEMIS auto-select an available ready device.

Using it with Claude Code

Run this from the repo directory, or accept the prompt that ./start.sh shows on first launch:

uv run artemis mcp --install claude

It writes to these user-level files:

  • ~/.claude.json — adds the artemis server to Claude Code’s global MCP config
  • claude_desktop_config.json — adds the same server to Claude Desktop
  • ~/.claude/rules/artemis.md — installs the testing rules in exactly one location, since Claude Code loads both ~/.claude/CLAUDE.md and ~/.claude/rules/*.md

--install all configures every supported AI IDE, so targeting claude keeps the change limited to Claude.

For Claude Code, ARTEMIS reports a finished background task with a native desktop notification and a JSONL audit log in notifications.jsonl. The reactive wakeup that resumes the conversation is Antigravity-only, so Claude Code checks results with mobile_manage_task(action="status").

How to use

Connect an Android device with USB Debugging enabled, or an emulator, then:

# 1. Clone repo & navigate to directory
git clone https://github.com/google/artemis.git && cd artemis

# 2. One-click launch (installs ADB, scrcpy, FFmpeg, and uv dependencies, then offers MCP setup)
./start.sh

# 3. Run a task directly from the CLI
uv run artemis run "Open Settings, find Battery and tell me current level" --profile flash

The launch opens http://localhost:8000 with a device connection wizard, live screen mirroring, prompt sandbox, and execution replays. Manage the server with uv run artemis status, uv run artemis restart, and uv run artemis stop.

Notes

  • LLM provider key required — .env.example asks you to configure at least one of Gemini, OpenAI, Anthropic, OpenRouter, or xAI. These calls are billed by the provider, separately from your Claude Code plan.
  • Android only — iOS devices and simulators are a roadmap item. If you need iOS and Android with the same tools, see Mobile MCP.
  • Requirements — Python 3.12+, plus ADB, scrcpy, FFmpeg, and uv, which ./start.sh detects and installs.
  • Personal phones — the Accessibility Helper adds a collapsed “Artemis test helper is running” notification and an entry under Settings > Accessibility. Per the README, it listens only on the phone itself and sends nothing elsewhere. Set ARTEMIS_HELPER_AUTO_INSTALL=false on shared or personal phones, and ARTEMIS_KEEP_DEVICE_AWAKE=false if the screen should time out.
  • Benchmark claims — the README reports a 99%+ completion rate on Google Research’s AndroidWorld benchmark (20+ apps, 100+ multi-step tasks). This is the project’s own figure.
  • Docs — MCP tools and notification channels are covered in the MCP Server README.
§ 7

See also

same category · curated
[01]
[Tool] Claude Quickstarts · A collection of projects designed to help developers quickly get started with building deployable applications using the Claude API. Runnable quickstarts cover a customer support agent, a financial data analyst, computer use, browser automation, and Claude Managed Agents apps for Slack, Linear, Sentry, and MCP. Some quickstarts let Claude Code drive the setup.
tool · claudekit.io / tools / claude-quickstarts
[02]
[Tool] Worktrunk · A CLI for git worktree management, designed for running AI agents in parallel. Worktrees are addressed by branch name, and `wt switch -c -x claude feat` creates a worktree and starts Claude Code in it. The Claude Code plugin adds activity tracking in `wt list` and routes the worktrees agents create through Worktrunk.
tool · claudekit.io / tools / worktrunk
[03]
[Plugin] Superpowers · A complete software development methodology for your coding agents, built on composable skills that enforce TDD, systematic debugging, and plan-driven execution.
tool · claudekit.io / tools / superpowers
§ 8

Frequently Asked Questions

frequently asked
§ 8.1
What is ARTEMIS?
ARTEMIS turns natural-language instructions into Android automation, executing testing workflows and everyday tasks on real devices and emulators. It ships a web console, a CLI, a Python SDK, and a native MCP server that lets AI assistants such as Claude Code drive test devices.
§ 8.2
How do I connect it to Claude Code?
Clone the repo, run `./start.sh`, then run `uv run artemis mcp --install claude` from the repo directory. This merges the MCP server into `~/.claude.json` and `claude_desktop_config.json`, and installs the testing rules to `~/.claude/rules/artemis.md`.
§ 8.3
Is ARTEMIS free?
It is open source under the Apache License 2.0. ARTEMIS runs its own model calls to operate the device, so you configure at least one LLM provider key (Gemini, OpenAI, Anthropic, OpenRouter, or xAI) in `.env`, and that usage is billed by the provider.
§ 8.4
Does it support iOS?
Not yet. ARTEMIS currently automates Android devices and emulators, and iOS Platform Expansion is listed on the roadmap.
§ 8.5
What's the difference between the Flash and Pro profiles?
Flash is a fast and token-efficient reactive loop where one model observes the live screen, thinks, and acts, at about 3-5s per step. Pro is a planning and verification workflow (about 15-40s per step) built as a Planner, Operator, and Checker graph that handles 100+ step long-horizon workflows.
§ 8.6
What does ARTEMIS install on my phone?
The first task installs the Artemis Accessibility Helper, a small accessibility service that reads the screen layout. Set `ARTEMIS_HELPER_AUTO_INSTALL=false` in `.env` to prevent automatic installation, or remove it any time with `uv run artemis helper uninstall`.