REPOGEO REPORT · LITE

callstackincubator/agent-device

Default branch main · commit 1987198f · scanned 5/15/2026, 7:17:08 AM

GitHub: 2,065 stars · 120 forks

AI VISIBILITY SCORE

40 /100

Critical

Category recall

0 / 2

Not recommended in any query

Rule findings

2 pass · 0 warn · 0 fail

Objective metadata checks

AI knows your name

3 / 3

Direct prompts that named your repo

HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface callstackincubator/agent-device, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION

highreadme#1

Reposition README's opening paragraph to emphasize AI agent control

Why:

CURRENT

Device automation CLI for AI agents. Mobile, TV, and desktop apps.

COPY-PASTE FIX

agent-device is a powerful CLI for AI agents to programmatically control iOS, Android, TV, and desktop applications. It enables coding agents to run real apps, inspect UI state, interact with elements, and collect debugging evidence.

highreadme#2

Add a 'Why for AI Agents?' section to the README

Why:

COPY-PASTE FIX

Add a new section, e.g., `## Why agent-device for AI Agents?` with content like: "Unlike traditional mobile automation tools (e.g., Appium, Detox, Maestro), `agent-device` is purpose-built for AI agents. It provides a token-efficient accessibility snapshot-based UI tree, allowing agents to understand and interact with apps programmatically, rather than relying on pixel-first screenshots. This enables agents to perform complex tasks, validate UI, and gather targeted debugging evidence efficiently."

mediumtopics#3

Refine and reorder repository topics

Why:

CURRENT

adb, agentic-ai, agents, android-emulator, automation, e2e-testing, expo, ios-simulator, mcp, mobile, react-native, testing, xcuitest

COPY-PASTE FIX

ai-agents, agentic-ai, mobile-automation, device-control, cli, e2e-testing, android, ios, automation, accessibility-testing, debugging-tools, react-native-testing

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall

0 / 2

0% of queries surface callstackincubator/agent-device

Avg rank

—

Lower is better. #1 = top recommendation.

Share of voice

Of all named tools, what % are you?

Top rival

appium/appium

Recommended in 2 of 2 queries

COMPETITOR LEADERBOARD

appium/appium · recommended 2×
wix/Detox · recommended 2×
Espresso · recommended 2×
XCUITest · recommended 2×
mobile-dev-inc/maestro · recommended 2×

CATEGORY QUERY
How can AI agents programmatically control iOS and Android devices for automated testing?
you: not recommended
AI recommended (in order):
1. Appium (appium/appium)
2. Detox (wix/Detox)
3. Espresso
4. XCUITest
5. Maestro (mobile-dev-inc/maestro)
6. Kobiton
7. Sauce Labs
8. BrowserStack
AI recommended 8 alternatives but never named callstackincubator/agent-device. This is the gap to close.
Show full AI answer
CATEGORY QUERY
What CLI tools exist for mobile app UI automation and collecting debugging evidence for e2e tests?
you: not recommended
AI recommended (in order):
1. Appium (appium/appium)
2. Detox (wix/Detox)
3. Maestro (mobile-dev-inc/maestro)
4. XCUITest
5. Espresso
6. Playwright (microsoft/playwright)
7. Cypress (cypress-io/cypress)
AI recommended 7 alternatives but never named callstackincubator/agent-device. This is the gap to close.
Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

Metadata completeness
pass
README presence
pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

Compared to common alternatives in this category, what is the core differentiator of callstackincubator/agent-device?
pass
AI named callstackincubator/agent-device explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
If a team adopts callstackincubator/agent-device in production, what risks or prerequisites should they evaluate first?
pass
AI named callstackincubator/agent-device explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
In one sentence, what problem does the repo callstackincubator/agent-device solve, and who is the primary audience?
pass
AI named callstackincubator/agent-device explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of callstackincubator/agent-device. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

Live preview

MARKDOWN (README)

[![RepoGEO](https://repogeo.com/badge/callstackincubator/agent-device.svg)](https://repogeo.com/en/r/callstackincubator/agent-device)

HTML

<a href="https://repogeo.com/en/r/callstackincubator/agent-device"><img src="https://repogeo.com/badge/callstackincubator/agent-device.svg" alt="RepoGEO" /></a>

Pro

Subscribe to Pro for deep diagnoses

callstackincubator/agent-device — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

Deep reports10 / month
Brand-free category queries5 vs 2 in Lite
Prioritized action items8 vs 3 in Lite