artemis — security grade SAFE, quality 64/100

Security audit verdict: SAFE · quality 64/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by google · Codex Skill · ★ 10.9k

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is artemis safe to install? View the security audit →

About artemis

Let AI assistants and test suites use real phones like a human. English • 中文文档 • Workflow Showcase • Quick Start • MCP for IDEs • Benchmarks • Discord Community Live

ai-agentsandroidgoogletest-automationtesting

Quick Facts

Stars10,908
Forks1,106
LanguagePython
CategoryCodex Skill
LicenseApache-2.0
Quality Score63.9994566557582/100
Open Issues120
Last Updated2026-10-01
Created2026-08-13
Platformsclaude-code, codex, python
Est. Tokens~17k

Compatible Skills

These tools work well together with artemis for enhanced workflows:

  • NanoJev — semantic(0.24)+complementary+same_lang+similar_pop+shared_platform (58%)
  • SeleniumBase — semantic(0.23)+complementary+same_lang+similar_pop+shared_platform (58%)
  • pydantic-ai — semantic(0.17)+complementary+same_lang+similar_pop+shared_platform (56%)
  • docker-android — semantic(0.16)+complementary+same_lang+similar_pop+shared_platform (56%)
  • harness-sdk — semantic(0.15)+complementary+same_lang+similar_pop+shared_platform (55%)

artemis alternative? Top 6 similar tools

Looking for a artemis alternative? If you're comparing artemis with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • lamda by firerpa · ⭐ 8.5k

    Android Full-Stack Device Control Platform: WebRTC/H.264 remote desktop, UI/OCR/image-matching automation, one

  • shortest by antiwork · ⭐ 5.7k

    QA via natural language AI tests

  • LibreChat by danny-avila · ⭐ 44.8k

    Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure,

  • activepieces by activepieces · ⭐ 24.9k

    AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with M

  • paseo by getpaseo · ⭐ 19.3k

    Orchestrate multiple coding agents from desktop and mobile

  • trigger.dev by triggerdotdev · ⭐ 16.5k

    Trigger.dev – build and deploy durable AI agents and workflows

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is artemis?

artemis is ARTEMIS turns natural-language instructions into reliable Android automation. It automates end-to-end workflows, captures logs, and integrates seamlessly with AI coding assistants such as Antigravity,. It is categorized as a Codex Skill with 10.9k GitHub stars.

What programming language is artemis written in?

artemis is primarily written in Python. It covers topics such as ai-agents, android, google.

How do I install or use artemis?

You can find installation instructions and usage details in the artemis GitHub repository at github.com/google/artemis. The project has 10.9k stars and 1106 forks, indicating an active community.

What license does artemis use?

artemis is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to artemis?

The top alternatives to artemis on Agent Skills Hub include lamda, shortest, LibreChat. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Codex Skill tools