CuaGuideAdvanced

Telemetry

Understanding and controlling Cua's anonymous usage collection

Cua collects anonymous usage statistics to improve the product. No personal data, screenshots, or conversation content is collected by default. You can opt out completely at any time.

What's Collected

By Default (Opt-Out)

Basic performance metrics:

  • System info - OS, OS version, Python version
  • Module initialization - When packages are imported and their versions
  • Performance - Agent run durations, step counts, token usage, API costs
  • Session tracking - Anonymous UUIDs for sessions and runs

Opt-In Only

Trajectory logging captures full conversation history and must be explicitly enabled:

  • User messages and agent responses
  • Computer actions and outputs
  • Agent reasoning traces

Never Collected

  • Personal information or user identifiers
  • API keys or credentials
  • File contents or application data
  • Screenshots (unless trajectory logging is enabled)
  • Text being typed or model outputs (unless trajectory logging is enabled)

Disabling Telemetry

Environment Variable

Set CUA_TELEMETRY_ENABLED to disable globally:

export CUA_TELEMETRY_ENABLED=false

Per Instance

Disable on individual objects:

from computer import Computer
from agent import ComputerAgent

# Disable for Computer
computer = Computer(
    os_type="linux",
    provider_type="docker",
    telemetry_enabled=False
)

# Disable for Agent
agent = ComputerAgent(
    model="anthropic/claude-sonnet-4-5-20250929",
    tools=[computer],
    telemetry_enabled=False
)

Check Status

print(computer.telemetry_enabled)  # True or False
print(agent.telemetry_enabled)     # True, False, or dict

Enabling Trajectory Logging

To opt in to full conversation logging:

agent = ComputerAgent(
    model="anthropic/claude-sonnet-4-5-20250929",
    tools=[computer],
    telemetry_enabled={"log_trajectory": True}
)

This sends complete conversation items to help improve Cua's models.

Events Reference

Computer SDK Events

EventDataTrigger
computer_initializedOS, OS version, Python versionComputer instance created
module_initModule name, version, Python versionPackage first imported

Agent SDK Events

EventDataTrigger
module_initModule name, version, Python versionPackage first imported
agent_session_startSession ID, agent type, model, system infoAgent instantiated
agent_run_startSession/run IDs, input size, message countagent.run() called
agent_run_endSession/run IDs, duration, steps, usageagent.run() completes
agent_stepSession/run IDs, step number, timestampEach agent iteration
agent_usageSession/run IDs, token counts, costUsage info received

Questions

Questions about telemetry? Open an issue on GitHub.

Was this page helpful?