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.
agent-device
CLI to control iOS and Android devices for AI agents
2.3kstars
128forks
TypeScript
adbagentic-aiagentsai-agentsandroid-emulatorautomatione2e-testingexpoflutterios-simulatormcpmobile
Quality signals
ActiveNo testsNo CIThin docsNo licensePopular
AI summary
Auto-generated overview of what this skill does and when to reach for it.
CLI that lets AI agents control real iOS/Android devices to inspect UIs, interact with apps, and capture debugging evidence for mobile, TV, and desktop apps.
Use this when
- Verify mobile changes on real devices before code review
- Debug regressions with screenshots, logs, and crash context
- Give AI coding agents a real app feedback loop during implementation
- Profile performance issues with CPU/memory samples and React profiles
- Turn exploratory app interactions into replayable e2e checks for CI
Don't use when
- Testing web apps in browsers (use Playwright/Selenium instead)
- Unit testing isolated code without UI (use Jest/JUnit)
- Automating non-mobile desktop apps (use native tools)
Capabilities
- Inspect app UI via accessibility snapshots and semantic element refs
- Interact with apps: tap, type, scroll, gestures, wait, assert state
- Capture evidence: screenshots, videos, logs, traces, network traffic
- Replay workflows from recorded .ad scripts for CI checks
- Run across platforms: iOS, Android, TV, desktop, simulators, emulators
- Support native, React Native, Expo, and Flutter apps
InstallMCP + SKILLInstall as a Claude Code skill
Universal installANY TOOL
$ npx skillcity@latest callstackincubator/agent-deviceAuto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor or Cline.
Requires Node.js 18+ (ships with npx).
Or install manually
# Install into ~/.claude/skills/ mkdir -p ~/.claude/skills/agent-device curl -fsSL https://raw.githubusercontent.com/callstackincubator/agent-device/main/SKILL.md -o ~/.claude/skills/agent-device/SKILL.md
Loading README…
Ask a simulated agent to run this skill. It loads the real SKILL.md and reasons over your task with NVIDIA.
agent-device — 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