# lycorp-jp/sim-use

Give your AI agent eyes and hands on iOS Simulator and Android emulator/devices.

Repository: https://github.com/lycorp-jp/sim-use
Canonical: https://ross.abutalabs.com/products/sim-use
Language: Swift
License: Apache-2.0
License Family: permissive
Topics: accessibility, ai-agents, ai-development, android-emulator, ios-simulator, mobile-automation
Last push: 2026-08-26T09:43:20+00:00

## Health v2 (maintenance only)
Score: 79/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 96, longevity 4
- inputs: {"age_days": 68, "days_push": 7, "days_rel": 27, "gap_med": 8.5, "n_releases_24m": 5}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1216, forks 78 (observed 2026-08-28T04:04:01.221906+00:00)

## What it is
sim-use is a cross-platform Swift CLI that gives AI agents the ability to observe and act on iOS Simulator and Android emulator/device screens. It converts the accessibility tree into a token-efficient text outline and lets agents tap elements by alias, ID, or label without coordinates.

## Use cases
- let an AI agent verify UI changes it made in an iOS simulator
- automate tapping through Android emulator screens with an LLM loop
- dump a compact accessibility outline of a mobile app screen for an LLM
- script mobile UI flows using element labels instead of coordinates
- close the observe-act-verify loop in agentic mobile development
- drive iOS Simulator and Android devices from a single CLI

## When to choose
- you want AI agents to interact with and verify mobile app UIs on iOS Simulator or Android emulators
- you need a token-efficient screen representation for LLM reasoning instead of screenshots
- you want coordinate-free UI automation driven by accessibility data

## When to avoid
- you need to automate desktop or web browsers rather than mobile simulators and devices
- you require pixel-level visual testing or screenshot-based verification
- you need a GUI-based record-and-playback mobile testing tool

## Facets
- artifact type: cli-tool
- maturity: active
- function: cli, workflow-automation, accessibility, agent-framework, developer-tools, testing
- domain: mobile-development, developer-tools, testing
- platform: cli, cross-platform
- tags: ios-simulator, android-emulator, mobile-automation, llm-agents, accessibility-tree, ui-automation, agentic-development, ai-agents, automation, macos

## Member repositories
- lycorp-jp/sim-use (main) score 79

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:01.221906+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:17:11.637198+00:00, confidence not recorded.
  - readme: https://github.com/lycorp-jp/sim-use (fetched 2026-08-28T04:04:01.221906+00:00, sha de2ad4511a2b)
- Data as of 2026-08-30T08:39:29.467469+00:00.