| title | Agno Telemetry |
|---|---|
| sidebarTitle | Telemetry |
| description | Control what usage data Agno collects |
| keywords | telemetry, privacy, data collection, usage tracking, disable telemetry, anonymous data |
Agno collects anonymous usage data about agents, teams, workflows, and AgentOS configurations to help improve the platform and provide better support.
**Privacy First:** No sensitive data (prompts, responses, user data, or API keys) is ever collected. All telemetry is anonymous and aggregated.Agno collects basic usage metrics for:
- Agent runs - Model providers, database types, feature usage
- Team runs - Multi-agent coordination patterns
- Workflow runs - Orchestration and execution patterns
- AgentOS launches - Platform usage and configurations
Here's what an agent run telemetry payload looks like:
{
"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-5.2",
"parser_model": {
"model_provider": "openai",
"model_name": "OpenAIResponses",
"model_id": "gpt-5.2",
},
"output_model": {
"model_provider": "openai",
"model_name": "OpenAIResponses",
"model_id": "gpt-5.2",
},
"has_tools": true,
"has_memory": false,
"has_reasoning": true,
"has_knowledge": true,
"has_input_schema": false,
"has_output_schema": false,
"has_team": true,
},
}You can disable telemetry in two ways:
Set the AGNO_TELEMETRY environment variable to false:
export AGNO_TELEMETRY=falseDisable telemetry for specific agents, teams, workflows, or AgentOS instances:
from agno.agent import Agent
from agno.models.openai import OpenAIResponses
# Disable telemetry for a specific agent
agent = Agent(
model=OpenAIResponses(id="gpt-5.2"),
telemetry=False
)This works for:
- Agents:
Agent(telemetry=False) - Teams:
Team(telemetry=False) - Workflows:
Workflow(telemetry=False) - AgentOS:
AgentOS(telemetry=False)
- View the Agent schema
- View the Team schema
- View the Workflow schema