OpenInference crewAI Instrumentation
Python auto-instrumentation library for LLM agents implemented with CrewAI
Crews are fully OpenTelemetry-compatible and can be sent to an OpenTelemetry collector for monitoring, such as Arize Phoenix or Arize AX.
Installation
pip install openinference-instrumentation-crewai
Quickstart
This quickstart shows you how to instrument your guardrailed LLM application
Install required packages.
pip install crewai crewai-tools arize-phoenix opentelemetry-sdk opentelemetry-exporter-otlp
Start Phoenix in the background as a collector. By default, it listens on http://localhost:6006. You can visit the app via a browser at the same address. (Phoenix does not send data over the internet. It only operates locally on your machine.)
python -m phoenix.server.main serve
Set up CrewAIInstrumentor to trace your crew and send the traces to Phoenix at the endpoint defined below.
from opentelemetry import trace
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import BatchSpanProcessor
from openinference.instrumentation.crewai import CrewAIInstrumentor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
from opentelemetry.sdk.trace.export import ConsoleSpanExporter, SimpleSpanProcessor
endpoint = "http://127.0.0.1:6006/v1/traces"
trace_provider = TracerProvider()
trace_provider.add_span_processor(SimpleSpanProcessor(OTLPSpanExporter(endpoint)))
CrewAIInstrumentor().instrument(tracer_provider=trace_provider)
Set up a simple crew to do research
import os
from crewai import Agent, Task, Crew, Process
from crewai_tools import SerperDevTool
os.environ["OPENAI_API_KEY"] = "YOUR_OPENAI_API_KEY"
os.environ["SERPER_API_KEY"] = "YOUR_SERPER_API_KEY"
search_tool = SerperDevTool()
# Define your agents with roles and goals
researcher = Agent(
role='Senior Research Analyst',
goal='Uncover cutting-edge developments in AI and data science',
backstory="""You work at a leading tech think tank.
Your expertise lies in identifying emerging trends.
You have a knack for dissecting complex data and presenting actionable insights.""",
verbose=True,
allow_delegation=False,
# You can pass an optional llm attribute specifying what model you wanna use.
# llm=ChatOpenAI(model_name="gpt-3.5", temperature=0.7),
tools=[search_tool]
)
writer = Agent(
role='Tech Content Strategist',
goal='Craft compelling content on tech advancements',
backstory="""You are a renowned Content Strategist, known for your insightful and engaging articles.
You transform complex concepts into compelling narratives.""",
verbose=True,
allow_delegation=True
)
# Create tasks for your agents
task1 = Task(
description="""Conduct a comprehensive analysis of the latest advancements in AI in 2024.
Identify key trends, breakthrough technologies, and potential industry impacts.""",
expected_output="Full analysis report in bullet points",
agent=researcher
)
task2 = Task(
description="""Using the insights provided, develop an engaging blog
post that highlights the most significant AI advancements.
Your post should be informative yet accessible, catering to a tech-savvy audience.
Make it sound cool, avoid complex words so it doesn't sound like AI.""",
expected_output="Full blog post of at least 4 paragraphs",
agent=writer
)
# Instantiate your crew with a sequential process
crew = Crew(
agents=[researcher, writer],
tasks=[task1, task2],
verbose=True,
process=Process.sequential
)
# Get your crew to work!
result = crew.kickoff()
print("######################")
print(result)
Event Listener Mode
CrewAIInstrumentor().instrument(...) without extra flags is the default
wrapper-based integration and remains the recommended path for standard Python
CrewAI applications.
Use use_event_listener=True only when CrewAI execution is surfaced through the
event bus rather than direct Python method calls, such as AMP / low-code CrewAI
usage. See examples/event_listener_crew.py
for that setup.
By default, event-listener mode also creates LLM spans from CrewAI's
LLMCall* events. That is useful when the listener is your only source of LLM
visibility. If you already instrument the underlying LLM client separately, or
if you want tests that focus only on crew / agent / tool structure to avoid
provider- and retry-driven LLM span count variability, disable them with:
CrewAIInstrumentor().instrument(
tracer_provider=trace_provider,
use_event_listener=True,
create_llm_spans=False,
)
More Info
1 maintainer
Metadata
1 maintainer
Release files for openinference-instrumentation-crewai 1.1.18
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| openinference_instrumentation_crewai-1.1.18.tar.gz | 27.6 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| openinference_instrumentation_crewai-1.1.18-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 58.0 kB
Release files / openinference_instrumentation_crewai-1.1.18.tar.gz
| Download URL | openinference_instrumentation_crewai-1.1.18.tar.gz |
|---|---|
| Size | 27.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
09b22b7e33bd9461b3526aa7d44af2aa2b975565969b48b0ffc04f5671528c1a
|
|
BLAKE2b-256 checksum How to use checksums |
f1ad97c9a374187df82b81aa7d058367524fb5f8bb8a20bdd0632114ea60d019
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 10, 2026.
Transparency logRelease files / openinference_instrumentation_crewai-1.1.18-py3-none-any.whl
| Download URL | openinference_instrumentation_crewai-1.1.18-py3-none-any.whl |
|---|---|
| Size | 30.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
171dad44c1ca97ca9aa0090e55220ffac7cd3b61503c2f07a39c1ef59d9fead4
|
|
BLAKE2b-256 checksum How to use checksums |
5d7b1cb363bb89aea0137d3e4faee296b392f54236f794363b7f10d85604ff04
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 10, 2026.
Transparency log
