{"title":"Automated iOS App Testing","slug":"automated-testing-ios","category":"guides","summary":"Use Synapse + Computer Control API to automate iOS app testing via Simulator.","audience":["human","llm"],"tags":["guide","ios","testing","automation"],"difficulty":"advanced","updated":"2026-06-27","word_count":297,"read_minutes":1,"lang":"en","translated":true,"requested_lang":"en","content_markdown":"\n# Automated iOS App Testing\n\nCombine Synapse's memory system with the Computer Control API to build\nLLM-driven iOS app tests. The LLM remembers test scenarios, learns from past\nfailures, and adapts to UI changes.\n\n## Architecture\n\n```\n┌──────────────┐ commands ┌──────────────┐ screenshots ┌──────────────┐\n│ LLM Agent │ ─────────────▶│ Synapse │ ────────────────▶ │ iOS Sim │\n│ (Claude) │ │ Computer │ ◀──────────────── │ (via agent) │\n└──────────────┘ │ Control │ results └──────────────┘\n │ └──────────────┘\n │ store/recall\n ▼\n┌──────────────┐\n│ Memories │ (test scenarios, past failures, UI patterns)\n└──────────────┘\n```\n\n## Prerequisites\n\n- Synapse account + Mind Key\n- Synapse MCP server configured in Claude Desktop\n- iOS Simulator with `screen-remote-agent` installed\n- Computer registered in Synapse (see [Computer Control API](/docs/api/computers))\n\n## Step 1: Register the Simulator Computer\n\nOn the Mac running iOS Simulator:\n\n```bash\n# Get install code from Synapse\ncurl -X POST https://synapse.schaefer.zone/computers/install-code \\\n -H \"Authorization: Bearer YOUR_MIND_KEY\" \\\n -d '{\"computer_name\":\"ios-sim\"}'\n# → { \"install_code\": \"ic_...\" }\n\n# Run screen-remote-agent on the Mac\n# (uses the install code to register)\n```\n\n## Step 2: Store Test Scenarios in Memory\n\nStore reusable test scenarios as memories:\n\n```python\nimport requests\n\ndef store_test_scenario(name, steps, app):\n requests.post(f\"{URL}/memory\",\n headers={\"Authorization\": f\"Bearer {MIND_KEY}\"},\n json={\n \"category\": \"skill\",\n \"key\": f\"test_scenario_{name}\",\n \"content\": f\"App: {app}\\nSteps:\\n\" + \"\\n\".join(steps),\n \"tags\": [\"test\", \"ios\", app],\n \"priority\": \"high\"\n })\n\nstore_test_scenario(\"login_flow\", [\n \"Launch app\",\n \"Tap email field\",\n \"Type test@example.com\",\n \"Tap password field\",\n \"Type password123\",\n \"Tap Login button\",\n \"Verify home screen appears\"\n], \"MyApp\")\n```\n\n## Step 3: LLM-Driven Test Execution\n\nIn Claude Desktop (with Synapse MCP configured):\n\n```\nRun the login_flow test scenario on the iOS Simulator.\nTake a screenshot after each step and verify the expected UI.\nIf any step fails, store the failure as a memory so we can\navoid it next time.\n```\n\nClaude will:\n\n1. Call `memory_search` to find the `test_scenario_login_flow` memory\n2. Call `computer_screenshot` to see the current state\n3. Execute each step via `computer_command_queue` (click, type)\n4. Verify results via screenshots\n5. Store any failures as `mistake` memories\n\n## Step 4: Self-Healing Tests\n\nWhen a test fails, store the failure and the recovery:\n\n```python\ndef store_test_failure(scenario, step, error, recovery):\n requests.post(f\"{URL}/memory\",\n headers={\"Authorization\": f\"Bearer {MIND_KEY}\"},\n json={\n \"category\": \"mistake\",\n \"key\": f\"failure_{scenario}_{step}\",\n \"content\": f\"Scenario: {scenario}\\nStep: {step}\\nError: {error}\\nRecovery: {recovery}\",\n \"tags\": [\"test\", \"failure\", \"ios\", scenario],\n \"priority\": \"high\"\n })\n\n# Example\nstore_test_failure(\"login_flow\", \"tap_login\",\n \"Login button not found at expected coordinates\",\n \"Button moved due to new logo. Search by accessibility label instead.\")\n```\n\nNext time the LLM runs the test, it recalls the failure and applies the\nrecovery automatically.\n\n## Step 5: Test Result Tracking\n\nTrack test runs as tasks:\n\n```python\ndef track_test_run(scenario, status, duration):\n requests.post(f\"{URL}/mind/task\",\n headers={\"Authorization\": f\"Bearer {MIND_KEY}\",\n \"Content-Type\": \"application/json\"},\n json={\n \"title\": f\"Test: {scenario}\",\n \"description\": f\"Status: {status}, Duration: {duration}s\",\n \"priority\": \"normal\"\n })\n```\n\n## Common Commands\n\n| Action | Command |\n|--------|---------|\n| Launch Simulator | `xcrun simctl launch booted com.example.app` |\n| Screenshot | `computer_screenshot` (via Synapse MCP) |\n| Tap at (x,y) | `computer_command_queue {type:\"click\", payload:{x,y}}` |\n| Type text | `computer_command_queue {type:\"type\", payload:{text:\"...\"}}` |\n| Press Home | `computer_command_queue {type:\"key\", payload:{keys:[\"Cmd\",\"Shift\",\"H\"]}}` |\n\n## Best Practices\n\n> [!TIP]\n> - **Store UI coordinates as memories** — UI changes, but the LLM can re-learn\n> - **Use accessibility labels** — more stable than coordinates\n> - **Store test data separately** — use variables for usernames, passwords\n> - **Run tests in clean state** — reset Simulator between runs\n> - **Log screenshots for failures** — useful for debugging\n\n## Next Steps\n\n- [Self-Healing Tests](/docs/guides/self-healing-tests)\n- [Computer Control API](/docs/api/computers)\n- [Memory Best Practices](/docs/guides/memory-best-practices)\n","content_html":"

Automated iOS App Testing

\n

Combine Synapse's memory system with the Computer Control API to build\nLLM-driven iOS app tests. The LLM remembers test scenarios, learns from past\nfailures, and adapts to UI changes.

\n

Architecture

\n
┌──────────────┐    commands    ┌──────────────┐    screenshots    ┌──────────────┐\n│  LLM Agent   │ ─────────────▶│  Synapse     │ ────────────────▶ │  iOS Sim     │\n│  (Claude)    │               │  Computer    │ ◀──────────────── │  (via agent) │\n└──────────────┘               │  Control     │    results        └──────────────┘\n       │                       └──────────────┘\n       │ store/recall\n       ▼\n┌──────────────┐\n│  Memories    │ (test scenarios, past failures, UI patterns)\n└──────────────┘

Prerequisites

\n\n

Step 1: Register the Simulator Computer

\n

On the Mac running iOS Simulator:

\n
# Get install code from Synapse\ncurl -X POST https://synapse.schaefer.zone/computers/install-code \\\n  -H "Authorization: Bearer YOUR_MIND_KEY" \\\n  -d '{"computer_name":"ios-sim"}'\n# → { "install_code": "ic_..." }\n\n# Run screen-remote-agent on the Mac\n# (uses the install code to register)

Step 2: Store Test Scenarios in Memory

\n

Store reusable test scenarios as memories:

\n
import requests\n\ndef store_test_scenario(name, steps, app):\n    requests.post(f"{URL}/memory",\n        headers={"Authorization": f"Bearer {MIND_KEY}"},\n        json={\n            "category": "skill",\n            "key": f"test_scenario_{name}",\n            "content": f"App: {app}\\nSteps:\\n" + "\\n".join(steps),\n            "tags": ["test", "ios", app],\n            "priority": "high"\n        })\n\nstore_test_scenario("login_flow", [\n    "Launch app",\n    "Tap email field",\n    "Type test@example.com",\n    "Tap password field",\n    "Type password123",\n    "Tap Login button",\n    "Verify home screen appears"\n], "MyApp")

Step 3: LLM-Driven Test Execution

\n

In Claude Desktop (with Synapse MCP configured):

\n
Run the login_flow test scenario on the iOS Simulator.\nTake a screenshot after each step and verify the expected UI.\nIf any step fails, store the failure as a memory so we can\navoid it next time.

Claude will:

\n
    \n
  1. Call memory_search to find the test_scenario_login_flow memory
    2. \n
  2. Call computer_screenshot to see the current state
    3. \n
  3. Execute each step via computer_command_queue (click, type)
    4. \n
  4. Verify results via screenshots
    5. \n
  5. Store any failures as mistake memories
    6. \n
\n

Step 4: Self-Healing Tests

\n

When a test fails, store the failure and the recovery:

\n
def store_test_failure(scenario, step, error, recovery):\n    requests.post(f"{URL}/memory",\n        headers={"Authorization": f"Bearer {MIND_KEY}"},\n        json={\n            "category": "mistake",\n            "key": f"failure_{scenario}_{step}",\n            "content": f"Scenario: {scenario}\\nStep: {step}\\nError: {error}\\nRecovery: {recovery}",\n            "tags": ["test", "failure", "ios", scenario],\n            "priority": "high"\n        })\n\n# Example\nstore_test_failure("login_flow", "tap_login",\n    "Login button not found at expected coordinates",\n    "Button moved due to new logo. Search by accessibility label instead.")

Next time the LLM runs the test, it recalls the failure and applies the\nrecovery automatically.

\n

Step 5: Test Result Tracking

\n

Track test runs as tasks:

\n
def track_test_run(scenario, status, duration):\n    requests.post(f"{URL}/mind/task",\n        headers={"Authorization": f"Bearer {MIND_KEY}",\n                 "Content-Type": "application/json"},\n        json={\n            "title": f"Test: {scenario}",\n            "description": f"Status: {status}, Duration: {duration}s",\n            "priority": "normal"\n        })

Common Commands

\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
ActionCommand
Launch Simulatorxcrun simctl launch booted com.example.app
Screenshotcomputer_screenshot (via Synapse MCP)
Tap at (x,y)computer_command_queue {type:"click", payload:{x,y}}
Type textcomputer_command_queue {type:"type", payload:{text:"..."}}
Press Homecomputer_command_queue {type:"key", payload:{keys:["Cmd","Shift","H"]}}
\n

Best Practices

\n

Next Steps

\n\n","urls":{"html":"/docs/guides/automated-testing-ios","text":"/docs/guides/automated-testing-ios?format=text","json":"/docs/guides/automated-testing-ios?format=json","llm":"/docs/guides/automated-testing-ios?format=llm"},"translations_available":["en","zh","hi","es","fr","ar","pt","ru","ja","de","it","ko","nl","pl","tr","sv","vi","th","id","uk"]}