google/artemis
ARTEMIS turns natural-language instructions into reliable Android automation. It automates end-to-end workflows, captures logs, and integrates seamlessly with…
★ 13.8KWeek rank 71 · star gain starts at the next snapshot
From the README
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 Demo: Setup driving routes and calculate total durations in Google Maps, then open YouTube to play a Coldplay song.
Setup prompt
Paste this into Cursor or Claude Code. It only includes install lines found in the README, and it asks the agent to review the code first.
Set up the GitHub repository google/artemis (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, Codex, and Claude Code. It also achieves 99%+ success rate on AndroidWorld Benchmark.). Repository: https://github.com/google/artemis Official install commands found in the README: git clone https://github.com/google/artemis.git && cd artemis Clone the repository and follow those steps. Do not invent package names or extra install commands. Review the code before running anything.
Buzz by window
Same mentions, three half-lives. This is not a star history. Star gain appears after a second daily snapshot.
- Today0.23
- Week0.98
- Month1.39
Spotted on
- X @jaseelck04Oct 24, 2026
- X @quangdigiazOct 22, 2026
Related
- affaan-m/ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode,…
- anthropics/claude-code
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining…
- pbakaus/impeccable
The design language that makes your AI harness better at design.
- cloudflare/security-audit-skill
A coding-agent skill for multi-phase security audits with independently verified, machine-readable findings