Skip to main content
Install the integration extra: 
pip install "agentx-python[crewai]" crewai

​
observer.kickoff()

Wraps crew.kickoff() for you. Task outputs are automatically captured as tool calls. 
from agentx import AgentX
from agentx.integrations.crewai import AgentXCrewObserver
from crewai import Agent, Task, Crew

client = AgentX(
    api_key="agx-xxxxxxxxxxxxxxxx",
    workspace_id="xxxxxxxxxxxx",  # optional
)
observer = AgentXCrewObserver(
    tracer=client.tracer,
    name="support-crew",
    metadata={"env": "production"},
)

researcher = Agent(
    role="Policy Researcher",
    goal="Find relevant company policies",
    backstory="You look up policies from the knowledge base.",
    verbose=False,
)
writer = Agent(
    role="Support Writer",
    goal="Write clear, friendly support responses",
    backstory="You turn policy details into helpful customer replies.",
    verbose=False,
)
crew = Crew(
    agents=[researcher, writer],
    tasks=[
        Task(
            description="Look up the cancellation policy and summarize it.",
            expected_output="A concise policy statement.",
            agent=researcher,
        ),
        Task(
            description="Write a friendly support reply about cancelling a subscription.",
            expected_output="A clear, helpful response to send to the customer.",
            agent=writer,
        ),
    ],
    verbose=False,
)

result = observer.kickoff(crew, inputs={"query": "cancel subscription"})
print(result.raw)

client.tracer.flush(timeout=10)

​
What gets traced

FieldSource
inputinputs dict passed to kickoff()
outputresult.raw (CrewOutput string)
latencyMsWall-clock time of the full crew run
toolCallsEach task output — description as name, raw as output
errorException message if crew.kickoff() raises

​
AgentXCrewObserver reference

AgentXCrewObserver(
    tracer: Tracer,
    name: str = "crewai-crew",
    metadata: dict | None = None,
    session_id: str | None = None,
)
ParameterDescription
tracerclient.tracer from your AgentX instance
nameLabel shown in the AgentX UI
metadataStatic key-value metadata attached to every trace
session_idLinks traces from the same conversation thread

​
observe() parameters

observer.observe(
    name: str | None = None,
    input: Any = None,
    metadata: dict | None = None,
    session_id: str | None = None,
) -> contextmanager
Inside the with block, assign span.output before exiting to set the trace output.
Call tracer.flush() before your process exits in scripts or one-shot jobs. In long-running servers it is not required — traces drain automatically in the background.