This cookbook shows how to add Maxim observability and tracing to your CrewAI agent applications in just one line of code. You’ll learn how to instrument CrewAI, log agent interactions, and view traces in the Maxim dashboard.

​
Prerequisites

​
1. Installation

Install the Maxim SDK via pip: 
pip install maxim-py
Or add to your requirements.txt: 
maxim-py

​
2. Set Up Environment Variables

Create a .env file in your project root: 
# Maxim API Configuration
MAXIM_API_KEY=your_api_key_here
MAXIM_LOG_REPO_ID=your_repo_id_here

​
3. Import Required Packages

from crewai import Agent, Task, Crew, Process
from maxim import Maxim
from maxim.config import Config              
from maxim.logger import LoggerConfig  
from maxim.logger.crewai import instrument_crewai

​
4. Instrument CrewAI with Maxim

Instrument CrewAI with just one line: 
import os
from dotenv import load_dotenv

load_dotenv()

maxim = Maxim(Config(api_key=os.environ["MAXIM_API_KEY"]))
instrument_crewai(maxim.logger(LoggerConfig(id=os.environ["MAXIM_LOG_REPO_ID"])))
You can enable debug logging for troubleshooting: 
instrument_crewai(maxim.logger(LoggerConfig(id=MAXIM_LOG_REPO_ID)), debug=True)

​
5. Create and Run Your CrewAI Application

# Create your agent
researcher = Agent(
    role='Senior Research Analyst',
    goal='Uncover cutting-edge developments in AI',
    backstory="You are an expert researcher at a tech think tank...",
    verbose=True,  # Enable verbose for detailed logs
)

# Define the task
research_task = Task(
    description="Research the latest AI advancements...",
    expected_output="",
    agent=researcher
)

# Configure and run the crew
crew = Crew(
    agents=[researcher],
    tasks=[research_task],
    verbose=True
)

try:
    result = crew.kickoff()
finally:
    maxim.cleanup()  # Ensure cleanup happens even if errors occur
That’s it! All your CrewAI agent interactions will now be logged and available in your Maxim dashboard.

​
6. Viewing Your Traces

After running your CrewAI application:
  • Log in to your Maxim Dashboard
  • Navigate to your repository
  • View detailed agent traces, including:
    • Agent conversations
    • Tool usage patterns
    • Performance metrics
    • Cost analytics

​
7. Troubleshooting

​
Common Issues

  • No traces appearing:
    • Ensure your API key and repository ID are correct
    • Ensure you’ve called instrument_crewai() before running your crew
    • Set debug=True in your instrument_crewai() call to surface any internal errors
  • Verbose logging:
    • Configure your agents with verbose=True to capture detailed logs
  • Order of operations:
    • Double-check that instrument_crewai() is called before creating or executing agents
crewai_traces.gif
For more details, see the CrewAI documentation and the Maxim Python SDK documentation.