# google/artemis > Google's tool for automating Android devices from natural-language instructions: drives apps, captures logs and screenshots, and integrates with AI assistants via MCP. - Magnitude: 3.6 out of 10 — Steady - Stars: 15,493 total · +49 stars measured 2026-10-29, 00:04–03:36 UTC, ≈ 232 by evening - Star trust: star growth looks organic - Category: AI agents · Language: Python · License: Apache-2.0 · Created: 2026-08-13 · Last push: 2026-10-01 - GitHub: https://github.com/google/artemis · Page: https://gitnova.dev/en/r/google/artemis - GitNova flagged it 30 days before GitHub Trending. ## Useful for - Run an end-to-end Android app test from a prompt in Claude Code via MCP - Collect Logcat and screenshots from a real device during a scenario run - Check UI stability in a long exploratory test on an emulator ## Why it’s here - Star-counter measurements on 2026-10-29 (UTC), 00:04–03:36: 15444 → 15493 stars (+49). This is the change over that interval. - Estimated end-of-day forecast: about +232 stars, using observed gains and the previous day. - Top new repositories in the last 4 months: #33. - About 35 forks a day — people are taking the code. ## Star trust Star growth looks organic. Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer. ## Numbers - Forks: 1,692 - Issues and pull requests: 218 - Watchers: 183 - Average over the last week: 271 per day - Usual pace: 214 per day - Stars in the last hour (measured): 16 ## Stars per day, last 30 days (oldest → newest, today is partial) 2026-09-30 … 2026-10-29: 83, 85, 62, 39, 46, 52, 44, 56, 65, 71, 57, 74, 70, 172, 96, 206, 143, 130, 454, 430, 261, 345, 188, 328, 411, 283, 220, 222, 209, 49 ## Magnitude by day, last 14 days 10-16 4.5, 10-17 4.2, 10-18 4.3, 10-19 5.7, 10-20 5.1, 10-21 4.2, 10-22 4.7, 10-23 3.9, 10-24 4.4, 10-25 4.6, 10-26 4.0, 10-27 3.6, 10-28 3.8, 10-29 3.6 ## Spotted in now - Top new repositories in the last 4 months: #33 ## Similar by description 1. **tester-army/e2e** — 2.6 · Steady · Developer tools · TypeScript · +19 stars measured 2026-10-29, 00:06–03:38 UTC, ≈ 91 by evening End-to-end testing framework for web and mobile apps: a test goal is described in natural language, an agent drives the app to reach it, and the result is checked with locators and assertions. Recorded agent steps replay without model… Full card: https://gitnova.dev/en/r/tester-army/e2e.md 2. **php/php-src** — 2.3 · Cooling · Other · C · +1 star measured 2026-10-29, 00:07–03:38 UTC, ≈ 11 by evening The source code for the PHP interpreter, a popular scripting language for web development. Allows building and testing the interpreter itself. Full card: https://gitnova.dev/en/r/php/php-src.md 3. **homeassistant-ai/ha-mcp** — 2.0 · Steady · AI agents · Python · +3 stars measured 2026-10-29, 00:07–03:39 UTC, ≈ 20 by evening An MCP server that lets AI assistants (Claude, ChatGPT, etc.) control Home Assistant: toggle devices, query states, call services and automations in natural language. Full card: https://gitnova.dev/en/r/homeassistant-ai/ha-mcp.md 4. **ChrisThoma/ios-device-mcp** — 0.0 · Quiet · TypeScript · Not enough measurements today MCP server that drives a real iPhone or iPad (not the simulator): build, install, tap, type, screenshots, logs, files and audio Full card: https://gitnova.dev/en/r/ChrisThoma/ios-device-mcp.md 5. **Imsharad/gmail-mcp-server** — 0.0 · Quiet · Python · Not enough measurements today A Gmail Model Context Protocol server for seamless integration with AI assistants Full card: https://gitnova.dev/en/r/Imsharad/gmail-mcp-server.md --- Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score. Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast. Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself. Data as of 2026-10-29 03:46 UTC, updated every 30 minutes.