Agent Device Callstack

↗ github.com/callstackincubator/agent-device official repository

device automation CLI that lets AI agents open apps, inspect UI, interact with elements, capture debugging evidence, and verify real app behavior on iOS, Andro…

toolSource repositoryRepository checked daily

Agentery price verdictNo pricing observedsource repository

SourcePublic repositorylicence not verified

Billing model—

Last checked28 Jul 2026pricing & liveness

What it does

The specific capability behind this listing, and where to get it.

device automation CLI that lets AI agents open apps, inspect UI, interact with elements, capture debugging evidence, and verify real app behavior on iOS, Android, TV, and desktop

CLI commands, .ad replay scripts, accessibility snapshots, MCP tool calls → structured accessibility snapshots, semantic refs, screenshots, videos, logs, traces, network traffic, performance samples

CursorCodexClaude CodeWindsurfMCPMaestroExpo (EAS)GitHub ActionsMCPautonomy: infrastructure

Official Agent Device Callstack links

RepositoryOpen ↗DocumentationOpen ↗MCP endpointOpen ↗API endpointOpen ↗Agentery niche comparisonView →

Price status · observed daily

Source repository available · no commercial pricing observed.

No price does not imply the product is free. Any code-host platform pricing is excluded.

Repository

Open

↗

github.com/callstackincubator/agent-device

Documentation

Open

↗

github.com/documentation

Is Agent Device Callstack good value?

Price is straightforward; the useful comparison is capability, compatibility and operational cost.

Source repository

Source repository available · no commercial pricing observed.

A public repository, but no identified licence or self-host evidence yet — so open-source / free-to-self-host is not asserted.

Observed commercial pricenone

NicheMobile Device Automation

Price benchmarknot applicable

What to compare instead

Check capability before deciding

Compare capability, compatibility and operational cost against comparable providers — Agentery keeps the price status explicit and never invents a verdict.

View the full niche →

Comparable Mobile Device Automation

Alternatives in the same niche, with observed price and liveness where available.

View the full niche →

Pokeclawmobile device automation

—No comparable commercial price observed

100% liveView profile →

See the MCP response behind this page · get_agent_profile()

See the MCP response behind this pageget_agent_profile

{
  "agent_id": "agent_device_callstack",
  "name": "Agent Device Callstack",
  "url": "https://github.com/callstackincubator/agent-device",
  "logo": "https://agentery.com/logos/CP-Y35998-256.png",
  "niche": "mobile-device-automation",
  "category": "developer-tools-infra",
  "short_summary": "device automation CLI that lets AI agents open apps, inspect UI, interact with elements, capture debugging evidence, and verify real app behavior on iOS, Andro…",
  "task_performed": "device automation CLI that lets AI agents open apps, inspect UI, interact with elements, capture debugging evidence, and verify real app behavior on iOS, Android, TV, and desktop",
  "inputs_accepted": [
    "CLI commands",
    ".ad replay scripts",
    "accessibility snapshots",
    "MCP tool calls"
  ],
  "outputs_produced": [
    "structured accessibility snapshots",
    "semantic refs",
    "screenshots",
    "videos",
    "logs",
    "traces",
    "network traffic",
    "performance samples",
    "crash context",
    "React profiles",
    "Maestro YAML exports"
  ],
  "integrations_available": [
    "Cursor",
    "Codex",
    "Claude Code",
    "Windsurf",
    "MCP",
    "Maestro",
    "Expo (EAS)",
    "GitHub Actions",
    "ADB",
    "XCTest",
    "AT-SPI"
  ],
  "protocols_or_interfaces": [
    "MCP"
  ],
  "industry_fit": [
    "developer tools"
  ],
  "autonomy_level": "infrastructure",
  "human_approval_needed": "unclear",
  "pricing_model": "unclear",
  "price": {
    "observed": false,
    "billing": "not_found",
    "currency": null,
    "lowest_monthly_usd": null,
    "monthly_usd": null,
    "headline": null,
    "summary": null,
    "confidence": "high",
    "source_url": "https://github.com/pricing",
    "checked_at": "2026-07-26T04:59:28.583Z",
    "amount": null,
    "display": null,
    "plans": [],
    "source": "render+llm"
  },
  "trust_or_rating_signal": [
    "2.8k GitHub stars",
    "155 forks",
    "MIT license"
  ],
  "evidence_quality": "high",
  "entity_type": "tool",
  "regulated_data_suitability": "unclear",
  "evidence_urls": [
    "https://github.com/callstackincubator/agent-device"
  ],
  "last_checked": "2026-06-16",
  "how_to_connect": {
    "website": "https://github.com/callstackincubator/agent-device",
    "docs": "https://github.com/documentation",
    "mcp": {
      "endpoint": "https://github.com/mcp.json",
      "transport": "http",
      "config_snippet": "{\n  \"mcpServers\": {\n    \"agent_device_callstack\": {\n      \"url\": \"https://github.com/mcp.json\"\n    }\n  }\n}"
    },
    "a2a": null,
    "api": {
      "docs_url": "https://github.com/developer",
      "endpoint": null
    },
    "protocols": []
  },
  "liveness": {
    "probed": true,
    "alive": true,
    "endpoint_kind": "site",
    "latency_ms": 764,
    "uptime_7d": 1,
    "checked_at": "2026-07-28T02:30:30.345Z",
    "consecutive_failures": 0,
    "status": "alive"
  },
  "price_extras": {
    "free_tier": null,
    "unit_cost": null
  },
  "reported_success": null,
  "feedback": "If you use this listing, call report_outcome afterwards — it sharpens rankings for everyone including you."
}