Discover the toolingbehind modern intelligence
The operating system for AI infrastructure discovery. Search a live map of MCP servers, AI agents, LLM tools, automation systems, and developer infrastructure.
mobilerun
Automate your mobile devices with natural language commands - an LLM agnostic mobile Agent 🤖
8.4kstars
878forks
Python
ai-agentsandroidandroid-automationhacktoberfestmobile-automation
Quality signals
StaleNo testsNo CIThin docsNo licensePopular
AI summary
Auto-generated overview of what this skill does and when to reach for it.
Control Android and iOS devices with natural language commands using LLM agents for automation, testing, or workflows.
Use this when
- Need to automate repetitive tasks on your phone
- Testing app behavior without manual interaction
- Extracting data from mobile apps via natural language
- Running mobile workflows on physical or virtual devices
- Debugging UI issues with screenshots and accessibility trees
Don't use when
- When you need real-time human interaction with the device
- For tasks requiring precise hardware-level control
- If the device has no accessibility or screenshot support
Capabilities
- Control Android/iOS via CLI, Python API, or Docker
- Inspect UI state with accessibility trees and screenshots
- Tap, swipe, type, and launch apps via natural language
- Multi-step workflow planning with reasoning mode
- Vision mode for apps without accessibility data
- Trace execution with Arize Phoenix or Langfuse
Install
Universal installANY TOOL
$ npx skillcity@latest droidrun/mobilerunAuto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor, Cline, OpenCode, Gemini CLI, Anti-Gravity, OpenClaw and Hermes.
Requires Node.js 18+ (ships with npx).
Prefer to set it up by hand? Clone the repository:
git clone https://github.com/droidrun/mobilerun.git
Loading README…
Ask a simulated agent to run this skill. It loads the real SKILL.md and reasons over your task with NVIDIA.
mobilerun — sandboxAI sandbox
Pick a quick prompt below or type your own — watch the agent execute this skill step by step.
guest@skillcity:~$Try a prompt