Agno automatically logs anonymised data about agents, teams and workflows, as well as AgentOS configurations. This helps us improve the Agno platform and provide better support.
No sensitive data is sent to the Agno servers. Telemetry is only used to improve the Agno platform.
Agno logs the following:
  • Agent runs
  • Team runs
  • Workflow runs
  • AgentOS Launches
Below is an example of the payload sent to the Agno servers for an agent run: 
{
    "session_id": "123",
    "run_id": "123",
    "sdk_version": "1.0.0",
    "type": "agent",
    "data": {
        "agent_id": "123",
        "db_type": "PostgresDb",
        "model_provider": "openai",
        "model_name": "OpenAIResponses",
        "model_id": "gpt-5-mini",
        "parser_model": {
            "model_provider": "openai",
            "model_name": "OpenAIResponses",
            "model_id": "gpt-5-mini",
        },
        "output_model": {
            "model_provider": "openai",
            "model_name": "OpenAIResponses",
            "model_id": "gpt-5-mini",
        },
        "has_tools": true,
        "has_memory": false,
        "has_reasoning": true,
        "has_knowledge": true,
        "has_input_schema": false,
        "has_output_schema": false,
        "has_team": true,
    },
}

​
Disabling Telemetry

You can disable this by setting AGNO_TELEMETRY=false in your environment or by setting telemetry=False on the agent, team, workflow or AgentOS. 
export AGNO_TELEMETRY=false
or: 
agent = Agent(model=OpenAIChat(id="gpt-5-mini"), telemetry=False)
See the Agent class reference for more details.