CrewAI | Respan Docs

CrewAI is a framework for orchestrating role-playing autonomous AI agents. It allows you to define agents with specific roles, goals, and tools, then coordinate them to accomplish complex tasks through collaborative workflows. Respan traces CrewAI runs with respan-instrumentation-crewai, which activates the OpenInference CrewAI instrumentor and exports crew, agent, task, tool, and LLM spans through the Respan tracing pipeline.

Set up Respan

Create an account at platform.respan.ai and grab an API key. For gateway, also add credits or a provider key.

Run npx @respan/cli setup to set up with your coding agent.

Example projects

Python examples

Tracing

Gateway

Setup

Install packages

$ pip install respan-ai respan-instrumentation-crewai crewai

Set environment variables

$ export OPENAI_API_KEY="YOUR_OPENAI_API_KEY"
$ export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"

OPENAI_API_KEY is used for LLM requests. RESPAN_API_KEY is used to export traces to Respan.

Initialize and run

Initialize Respan before importing CrewAI so the instrumentor can patch CrewAI early.

1 from respan import Respan
2 from respan_instrumentation_crewai import CrewAIInstrumentor
3 
4 respan = Respan(instrumentations=[CrewAIInstrumentor()])
5 
6 from crewai import Agent, Crew, Task
7 
8 researcher = Agent(
9     role="Researcher",
10     goal="Research and summarize the latest AI trends",
11     backstory="You are a senior AI researcher with years of experience.",
12 )
13 
14 writer = Agent(
15     role="Writer",
16     goal="Write a concise report based on the research",
17     backstory="You are a technical writer who excels at clear communication.",
18 )
19 
20 research_task = Task(
21     description="Research the latest trends in AI agent frameworks.",
22     expected_output="A summary of key trends and developments.",
23     agent=researcher,
24 )
25 
26 write_task = Task(
27     description="Write a brief report based on the research findings.",
28     expected_output="A well-structured report in markdown format.",
29     agent=writer,
30 )
31 
32 crew = Crew(
33     agents=[researcher, writer],
34     tasks=[research_task, write_task],
35 )
36 
37 result = crew.kickoff()
38 print(result)
39 respan.flush()

View your trace

Open the Traces page to see your CrewAI workflow with agent spans, task execution, tool usage, and LLM calls.

Configuration

Parameter	Type	Default	Description
`api_key`	`str \| None`	`None`	Falls back to `RESPAN_API_KEY` env var.
`base_url`	`str \| None`	`None`	Falls back to `RESPAN_BASE_URL` env var.
`instrumentations`	`list`	`[]`	Plugin instrumentations to activate, such as `CrewAIInstrumentor()`.
`customer_identifier`	`str \| None`	`None`	Default customer identifier for all spans.
`metadata`	`dict \| None`	`None`	Default metadata attached to all spans.
`environment`	`str \| None`	`None`	Environment tag (e.g. `"production"`).

CrewAIInstrumentor(use_event_listener=True, create_llm_spans=True, **kwargs) passes keyword arguments through to the underlying OpenInference CrewAI instrumentor.

Attributes

In Respan()

Set defaults at initialization. These apply to all spans.

1 from respan import Respan
2 from respan_instrumentation_crewai import CrewAIInstrumentor
3 
4 respan = Respan(
5     instrumentations=[CrewAIInstrumentor()],
6     customer_identifier="user_123",
7     metadata={"service": "crew-api", "version": "1.0.0"},
8 )

With propagate_attributes

Override per-request using a context scope.

1 from respan import Respan, propagate_attributes
2 from respan_instrumentation_crewai import CrewAIInstrumentor
3 
4 respan = Respan(instrumentations=[CrewAIInstrumentor()])
5 
6 from crewai import Agent, Crew, Task
7 
8 def handle_request(user_id: str, topic: str):
9     with propagate_attributes(
10         customer_identifier=user_id,
11         thread_identifier="conv_abc_123",
12         metadata={"plan": "pro"},
13     ):
14         researcher = Agent(
15             role="Researcher",
16             goal=f"Research {topic}",
17             backstory="Expert researcher.",
18         )
19         task = Task(
20             description=f"Research {topic}",
21             expected_output="Summary",
22             agent=researcher,
23         )
24         crew = Crew(agents=[researcher], tasks=[task])
25         print(crew.kickoff())

Attribute	Type	Description
`customer_identifier`	`str`	Identifies the end user in Respan analytics.
`thread_identifier`	`str`	Groups related messages into a conversation.
`metadata`	`dict`	Custom key-value pairs. Merged with default metadata.

Decorators (optional)

Decorators are not required. All CrewAI agent steps, tasks, and LLM calls are auto-traced by the instrumentor. Use @workflow and @task to add structure when you want to group related crews into a named workflow with nested tasks.

1 from respan import Respan, workflow, task
2 from respan_instrumentation_crewai import CrewAIInstrumentor
3 
4 respan = Respan(instrumentations=[CrewAIInstrumentor()])
5 
6 from crewai import Agent, Crew, Task
7 
8 @task(name="run_research_crew")
9 def run_research_crew(topic: str) -> str:
10     researcher = Agent(
11         role="Researcher",
12         goal=f"Research {topic}",
13         backstory="Expert.",
14     )
15     research_task = Task(
16         description=f"Research {topic}",
17         expected_output="Findings.",
18         agent=researcher,
19     )
20     crew = Crew(agents=[researcher], tasks=[research_task])
21     return str(crew.kickoff())
22 
23 @workflow(name="content_pipeline")
24 def pipeline(topic: str):
25     findings = run_research_crew(topic)
26     print(findings)
27 
28 pipeline("AI agent frameworks")
29 respan.flush()

Examples

Tool calls

Tool calls are automatically captured as spans with inputs, outputs, and timing.

1 from respan import Respan
2 from respan_instrumentation_crewai import CrewAIInstrumentor
3 
4 respan = Respan(instrumentations=[CrewAIInstrumentor()])
5 
6 from crewai import Agent, Crew, Task
7 from crewai.tools import tool
8 
9 @tool
10 def get_weather(city: str) -> str:
11     """Get the current weather for a city."""
12     return f"Sunny, 22C in {city}"
13 
14 researcher = Agent(
15     role="City Researcher",
16     goal="Gather weather data for a city",
17     backstory="You collect city data using available tools.",
18     tools=[get_weather],
19 )
20 
21 task = Task(
22     description="Research the weather in Paris.",
23     expected_output="Weather data for Paris.",
24     agent=researcher,
25 )
26 
27 crew = Crew(agents=[researcher], tasks=[task])
28 print(crew.kickoff())
29 respan.flush()