Skip to main content
AgentDbg’s CrewAI integration registers execution hooks that tap into CrewAI’s native before/after call lifecycle. Import the adapter once and every LLM invocation and tool execution from your crew or flow is automatically captured in the active AgentDbg run—including agent role, task description, and timing metadata.

​
What gets captured

The adapter hooks into four CrewAI execution points:
  • LLM calls (before_llm_call / after_llm_call) — records model name, prompt messages, response, and duration as an LLM_CALL event.
  • Tool calls (before_tool_call / after_tool_call) — records tool name, input arguments, result, and duration as a TOOL_CALL event.
Framework-specific context from each call is stored in meta.crewai.*:
FieldDescription
meta.crewai.executor_idIdentity of the executor running the call
meta.crewai.iterationsIteration count at the time of the call
meta.crewai.duration_msElapsed time in milliseconds for the call
meta.agent_roleThe role of the agent making the call
meta.task_descDescription of the task being executed

​
Installation

Install AgentDbg with the CrewAI extra: 
pip install "agentdbg[crewai]"
This installs crewai[tools] alongside AgentDbg. If you import the integration without crewai present, you get a clear ImportError with install instructions.

​
Setting up the adapter

1

Install the package

pip install "agentdbg[crewai]"
2

Import the integration module

Importing agentdbg.integrations.crewai registers the execution hooks automatically. Import it once, anywhere before your crew or flow runs:
import agentdbg
from agentdbg.integrations import crewai as adbg_crewai  # registers hooks
3

Wrap your entrypoint with @trace

The adapter only records events while an active AgentDbg run is open. Wrap the function that calls crew.kickoff() or flow.kickoff():
@agentdbg.trace
def run_crew():
    result = my_crew.kickoff()
    return result
4

Run your crew or flow

Call your traced function normally:
run_crew()
Then open the timeline:
agentdbg view

​
Full example

import agentdbg
from agentdbg.integrations import crewai as adbg_crewai  # registers hooks


@agentdbg.trace(name="my crewai run")
def run_crew():
    # Your crew.kickoff() or flow.kickoff() call goes here.
    result = my_crew.kickoff()
    return result


if __name__ == "__main__":
    run_crew()
    print("Run complete. View with: agentdbg view")

​
Hook ordering caveat

CrewAI runs execution hooks in registration order. If another before_llm_call or before_tool_call hook registered before AgentDbg’s returns False and blocks execution, the AgentDbg hook may not run for that specific call—and that call will not appear in the trace.
If you register your own before-hooks on CrewAI, make sure they do not return False unless you intentionally want to block execution. Returning False from a before-hook prevents all subsequent hooks for that call from running.

​
What’s coming

The following adapter is planned and not yet available:
  • Agno — adapter for Agno-based agents.
The adapter requires an active AgentDbg run. Wrap your entrypoint with @trace or traced_run(...).