Trace CrewAI agents

LangSmith can capture traces generated by CrewAI using OpenTelemetry instrumentation. This guide shows you how to automatically capture traces from your CrewAI multi-agent workflows and send them to LangSmith for monitoring and analysis.

In an agent-based workspace, create an agent once before sending traces. Use agent addressing to select its identifier and environment. If an integration requires project_name, use the selected environment’s tracer_session_name as a compatibility value.

Installation

Install the required packages using your preferred package manager:

pip install langsmith crewai opentelemetry-instrumentation-crewai opentelemetry-instrumentation-openai

uv add langsmith crewai opentelemetry-instrumentation-crewai opentelemetry-instrumentation-openai

Setup

1. Configure environment variables

Sending traces to an agent requires langsmith>=0.14.9. Set your API keys, agent identifier, and environment:

export LANGSMITH_API_KEY=<your_langsmith_api_key>
export LANGSMITH_AGENT_ID="<your-agent-id>"
export LANGSMITH_AGENT_ENVIRONMENT="local"
export OPENAI_API_KEY=<your_openai_api_key>

2. Configure OpenTelemetry integration

In your CrewAI agent, configure the LangSmith OpenTelemetry integration along with the CrewAI and OpenAI instrumentors:

from langsmith.integrations.otel import OtelSpanProcessor
from opentelemetry import trace
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.instrumentation.crewai import CrewAIInstrumentor
from opentelemetry.instrumentation.openai import OpenAIInstrumentor

# Get or create tracer provider
current_provider = trace.get_tracer_provider()
if isinstance(current_provider, TracerProvider):
    tracer_provider = current_provider
else:
    tracer_provider = TracerProvider()
    trace.set_tracer_provider(tracer_provider)

# Add OtelSpanProcessor to the tracer provider
tracer_provider.add_span_processor(OtelSpanProcessor())

# Instrument CrewAI and OpenAI
CrewAIInstrumentor().instrument(tracer_provider=tracer_provider)
OpenAIInstrumentor().instrument(tracer_provider=tracer_provider)

3. Create and run your CrewAI agent

Once configured, your CrewAI agent will automatically send traces to LangSmith:

from crewai import Agent, Crew, Task
from crewai.llm import LLM
from langsmith.integrations.otel import OtelSpanProcessor
from opentelemetry import trace
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.instrumentation.crewai import CrewAIInstrumentor
from opentelemetry.instrumentation.openai import OpenAIInstrumentor

# Configure OpenTelemetry
current_provider = trace.get_tracer_provider()
if isinstance(current_provider, TracerProvider):
    tracer_provider = current_provider
else:
    tracer_provider = TracerProvider()
    trace.set_tracer_provider(tracer_provider)

tracer_provider.add_span_processor(OtelSpanProcessor())

# Instrument CrewAI and OpenAI
CrewAIInstrumentor().instrument(tracer_provider=tracer_provider)
OpenAIInstrumentor().instrument(tracer_provider=tracer_provider)

# Define your agent
llm = LLM(model="gpt-6-luna")

coder = Agent(
    role="Software developer",
    goal="Write clear, concise code on demand",
    backstory="An expert coder with a keen eye for software trends.",
    verbose=True,
    llm=llm,
)

# Define your task
task = Task(
    description="Write a Python function that checks if a number is prime.",
    expected_output="A clear and concise Python function with documentation.",
    agent=coder,
)

# Create and run the crew
crew = Crew(
    agents=[coder],
    tasks=[task],
    verbose=True,
)

def run_crew():
    result = crew.kickoff()
    return result

if __name__ == "__main__":
    output = run_crew()
    print(output)

Advanced usage

Custom metadata and tags

You can add custom metadata to your traces by setting span attributes:

from opentelemetry import trace

tracer = trace.get_tracer(__name__)

def run_crew_with_metadata():
    with tracer.start_as_current_span("crewai_workflow") as span:
        span.set_attribute("langsmith.metadata.crew_type", "code_generation")
        span.set_attribute("langsmith.metadata.agent_count", "1")
        span.set_attribute("langsmith.span.tags", "crewai,code-generation")

        result = crew.kickoff()
        return result

Combining with other instrumentors

You can combine CrewAI instrumentation with other OpenTelemetry instrumentors:

from opentelemetry.instrumentation.crewai import CrewAIInstrumentor
from opentelemetry.instrumentation.openai import OpenAIInstrumentor

# Initialize multiple instrumentors
CrewAIInstrumentor().instrument(tracer_provider=tracer_provider)
OpenAIInstrumentor().instrument(tracer_provider=tracer_provider)

Resources

Connect these docs to your agent of choice via MCP for real-time answers.

Edit this page on GitHub or file an issue.

Tracing setup

Configuration & troubleshooting

Installation

Setup

1. Configure environment variables

2. Configure OpenTelemetry integration

3. Create and run your CrewAI agent

Advanced usage

Custom metadata and tags

Combining with other instrumentors

Resources

​Installation

​Setup

​1. Configure environment variables

​2. Configure OpenTelemetry integration

​3. Create and run your CrewAI agent

​Advanced usage

​Custom metadata and tags

​Combining with other instrumentors

​Resources

Installation

Setup

1. Configure environment variables

2. Configure OpenTelemetry integration

3. Create and run your CrewAI agent

Advanced usage

Custom metadata and tags

Combining with other instrumentors

Resources