CrewAI

Orchestrate AI agent teams with CrewAI and Adaline.

CrewAI

Use the Adaline CrewAI observer to send CrewAI crew executions into Adaline. The integration wraps an existing crew and observes its kickoff lifecycle without changing the crew or task logic itself.

Prerequisites

Before you start, make sure you have:

• An Adaline account.
• A workspace API key — create one under Settings → API keys.
• Your project ID — copy it from Monitor → Copy Project ID.

See Integrate your AI agent for a full walkthrough.

Set both as environment variables before running the examples on this page:

export ADALINE_API_KEY="your-api-key"
export ADALINE_PROJECT_ID="your-project-id"

Install

pip install adaline-client adaline-crewai crewai

Initialize Adaline

Create an Adaline client, then initialize a monitor for the target project.

import os

from adaline import Adaline

adaline = Adaline(api_key=os.environ["ADALINE_API_KEY"])
monitor = adaline.init_monitor(project_id=os.environ["ADALINE_PROJECT_ID"])

For production guidance — buffering, batching, retries, serverless flushing, and graceful shutdown — see Instrument with the Adaline SDK.

Wrap a CrewAI crew

Create an AdalineCrewAIObserver, then wrap the crew you want to observe.

from adaline_crewai import AdalineCrewAIObserver

observer = AdalineCrewAIObserver(monitor=monitor)
wrapped = observer.wrap_crew(crew)

Basic example

This example keeps the integration intentionally small: one crew with one agent and one task, observed through wrap_crew.

import asyncio

from crewai import Agent, Crew, Task

from adaline_crewai import AdalineCrewAIObserver

async def main():
    observer = AdalineCrewAIObserver(
        monitor=monitor,
        tags=["crewai"],
    )

    agent = Agent(
        role="greeter",
        goal="reply with a single word greeting",
        backstory="You respond concisely.",
        llm="gpt-4o-mini",
        allow_delegation=False,
        verbose=False,
    )
    task = Task(
        description="Reply with exactly one word: 'hello'.",
        agent=agent,
        expected_output="hello",
    )
    crew = Crew(agents=[agent], tasks=[task], verbose=False)

    wrapped = observer.wrap_crew(crew)
    result = wrapped.kickoff()

    await monitor.flush()


asyncio.run(main())

Use an existing parent trace or span

The CrewAI observer accepts:

• parent_trace
• parent_span

Pass one or the other, but not both.

What the observer captures

The CrewAI integration is designed to capture crew execution activity, including:

• a root observation for the crew kickoff
• serialized task and agent input metadata
• step callbacks emitted during the run
• child spans under an Adaline parent when provided

This page focuses on how to wrap the crew. The exact span tree depends on the CrewAI run behavior and step callbacks emitted during execution.

Next steps

Instrument with the Adaline SDK

Monitor lifecycle, buffering and batching, retries, serverless flushing, and graceful shutdown.

SDK reference

Full class and type reference for the TypeScript and Python SDKs.

All integrations

Browse every framework and AI-provider integration Adaline supports.

View your logs

Open Adaline to see traces and spans land in your project.