Skip to content
CrewAI Documentation

Webhook Streaming

Overview

Section titled “Overview”

Enterprise Event Streaming lets you receive real-time webhook updates about your crews and flows deployed to CrewAI AMP, such as model calls, tool usage, and flow steps.

Usage

Section titled “Usage”

When using the Kickoff API, include a webhooks object to your request, for example:

{
  "inputs": { "foo": "bar" },
  "webhooks": {
    "events": ["crew_kickoff_started", "llm_call_started"],
    "url": "https://your.endpoint/webhook",
    "realtime": false,
    "authentication": {
      "strategy": "bearer",
      "token": "my-secret-token"
    }
  }
}

If realtime is set to true, each event is delivered individually and immediately, at the cost of crew/flow performance.

Webhook Format

Section titled “Webhook Format”

Each webhook sends a list of events:

{
  "events": [
    {
      "id": "event-id",
      "execution_id": "crew-run-id",
      "timestamp": "2025-02-16T10:58:44.965Z",
      "type": "llm_call_started",
      "data": {
        "model": "gpt-4",
        "messages": [
          { "role": "system", "content": "You are an assistant." },
          { "role": "user", "content": "Summarize this article." }
        ]
      }
    }
  ]
}

The data object structure varies by event type. Refer to the event list on GitHub.

As requests are sent over HTTP, the order of events can’t be guaranteed. If you need ordering, use the timestamp field.

Supported Events

Section titled “Supported Events”

CrewAI supports both system events and custom events in Enterprise Event Streaming. These events are sent to your configured webhook endpoint during crew and flow execution.

Flow Events:

Section titled “Flow Events:”
  • flow_created
  • flow_started
  • flow_finished
  • flow_plot
  • method_execution_started
  • method_execution_finished
  • method_execution_failed

Agent Events:

Section titled “Agent Events:”
  • agent_execution_started
  • agent_execution_completed
  • agent_execution_error
  • lite_agent_execution_started
  • lite_agent_execution_completed
  • lite_agent_execution_error
  • agent_logs_started
  • agent_logs_execution
  • agent_evaluation_started
  • agent_evaluation_completed
  • agent_evaluation_failed

Crew Events:

Section titled “Crew Events:”
  • crew_kickoff_started
  • crew_kickoff_completed
  • crew_kickoff_failed
  • crew_train_started
  • crew_train_completed
  • crew_train_failed
  • crew_test_started
  • crew_test_completed
  • crew_test_failed
  • crew_test_result

Task Events:

Section titled “Task Events:”
  • task_started
  • task_completed
  • task_failed
  • task_evaluation

Tool Usage Events:

Section titled “Tool Usage Events:”
  • tool_usage_started
  • tool_usage_finished
  • tool_usage_error
  • tool_validate_input_error
  • tool_selection_error
  • tool_execution_error

LLM Events:

Section titled “LLM Events:”
  • llm_call_started
  • llm_call_completed
  • llm_call_failed
  • llm_stream_chunk

LLM Guardrail Events:

Section titled “LLM Guardrail Events:”
  • llm_guardrail_started
  • llm_guardrail_completed

Memory Events:

Section titled “Memory Events:”
  • memory_query_started
  • memory_query_completed
  • memory_query_failed
  • memory_save_started
  • memory_save_completed
  • memory_save_failed
  • memory_retrieval_started
  • memory_retrieval_completed

Knowledge Events:

Section titled “Knowledge Events:”
  • knowledge_search_query_started
  • knowledge_search_query_completed
  • knowledge_search_query_failed
  • knowledge_query_started
  • knowledge_query_completed
  • knowledge_query_failed

Reasoning Events:

Section titled “Reasoning Events:”
  • agent_reasoning_started
  • agent_reasoning_completed
  • agent_reasoning_failed

Event names match the internal event bus. See GitHub for the full list of events.

You can emit your own custom events, and they will be delivered through the webhook stream alongside system events.

GitHub

Full list of events

Need Help?

Contact our support team for assistance with webhook integration or troubleshooting.