Skip to main content

Crewai OpenTelemetry Integration

Overview

This integration provides support for using OpenTelemetry with the Crewai framework. It enables tracing and monitoring of applications built with Crewai.

Installation

  1. Install traceAI Crewai
pip install traceAI-crewai
  1. Install Crewai and Crewai_tools
pip install crewai crewai_tools

Set Environment Variables

Set up your environment variables to authenticate with FutureAGI

import os

os.environ["FI_API_KEY"] = FI_API_KEY
os.environ["FI_SECRET_KEY"] = FI_SECRET_KEY

# Set these before importing CrewAI to opt out of its separate native telemetry.
os.environ["CREWAI_DISABLE_TELEMETRY"] = "true"
os.environ["CREWAI_DISABLE_TRACKING"] = "true"

Privacy and credentials

Structural guarantee: framework configuration is not content

The instrumentor never exports an LLM, Agent, Crew, Task, Tool or client object itself, and never calls its repr, str, model_dump, dict, vars or generic JSON serializer to capture configuration. LLM API keys, base URLs (including URLs with userinfo), configuration headers and credentials are not selected. This does not depend on finding a secret's spelling or value.

The complete wrapper inventory is:

Wrapper Explicit input projection Explicit result projection
Task._execute_core Task description, expected output and application context; no agent or tool argument object TaskOutput.json_dict when it is a plain dictionary, otherwise TaskOutput.raw; plain application results
Crew.kickoff Application inputs; named agent/task business metadata below CrewOutput.json_dict when it is a plain dictionary, otherwise CrewOutput.raw; prompt/completion/total usage counts
ToolUsage._use ToolCalling.tool_name, ToolCalling.arguments; tool name only from the runtime tool Plain application result; no tool configuration

Crew metadata selects only crew/task keys and UUIDs; agent role, goal, backstory, key, UUID, verbosity, iteration/rate limits, delegation flag and tool names; and task description, expected output, UUID, execution/human-input flags, assigned agent role/key, context task descriptions and tool names. Task description and expected output are also emitted as formatted aliases when share_crew=True. Agent.execute_task and LLM calls have no additional wrappers in this package: they execute inside the task span and their arguments/results are not serialized independently. Separately installed LLM instrumentors have their own policies.

Opaque runtime objects nested in application data are replaced with [omitted runtime object], without inspecting their attributes. The guarantee is about framework configuration objects, not credentials deliberately copied into application prose or a plain dictionary. Instrumentation preserves application arguments, results and raised exceptions.

Application content: a field-name policy, not a universal secret detector

With content capture on, task/tool inputs and outputs are application content. The following policy applies to plain dictionaries, lists and tuples (copied without mutation), and complete JSON object/array strings. It also applies to context and span/event attributes, including structured log.body attributes. It does not filter independent application logging pipelines or console output.

Names are case-insensitive; an initial X-/X_ prefix and punctuation/separators are normalized away. Dot/bracket field paths are inspected component by component, including nested dictionary paths. A field and all its descendants are replaced by __REDACTED__ if the normalized component contains any of these markers:

  • apikey, accesskey, privatekey, clientkey, signingkey, subscriptionkey, applicationkey, masterkey;
  • token, secret, password, passwd, passphrase, credential, auth, cookie, session, signature, bearer, jwt, otp.

pin matches a whole normalized component only. Adjacent components are also combined for the eight *key markers above, so client.api.key and client[private][key] match their single-field equivalents.

Header interpretation requires an explicit field whose normalized name ends in headers (for example headers, request_headers, rawHeaders):

  • Dictionaries with credential-named header keys;
  • Two-item name/value pairs and collections of pairs;
  • Alternating name/value lists such as Node's rawHeaders;
  • Records with a name, key or header selector and a value field;
  • Flattened dot/bracket records with those selectors, or 0/1 selectors, including descendants of list-valued value fields in one attribute batch.

A credential-named header selector preserves its name but redacts the entire paired value. Outside a named headers field, pairs and {name, value} records are ordinary business data, never inferred to be headers. For example, topics=['authentication', 'billing'], business tables and product records keep their values.

The exact normalized metadata exceptions below remain visible (children are still inspected). These cover standard token counters, generation limits, tokenizer metadata, author metadata and non-secret session/service metadata:

acceptedpredictiontokens, apisecretid, audiotokens, author, authoremail; authorid, authority, authorname, authors, authorship; authorurl, cachecreationinputtokens, cachedcontenttokencount, cachedinputtokens, cachedtokencount; cachedtokens, cachereadinputtokens, cachereadtokens, cachewriteinputtokens, cachewritetokens; candidatestokencount, completiontokencount, completiontokens, completiontokensdetails, consultokenttl; inputtokencount, inputtokens, inputtokensdetails, maxcompletiontokens, maxinputtokens; maxnewtokens, maxoutputtokens, maxtokens, numtokens, outputtokencount; outputtokens, outputtokensdetails, promptcachehittokens, promptcachemisstokens, prompttokencount; prompttokens, prompttokensdetails, reasoningtokencount, reasoningtokens, rejectedpredictiontokens; securitytokenid, servicetokencount, sessioncount, sessionduration, sessiondurationms; subjecttokentype, thoughtstokencount, tokencount, tokenid, tokenizer; tokenizername, tokenizerversion, tokensused, tokenusage, tooluseprompttokencount; totaltokencount, totaltokens, vaulttokencount.

These are field-name rules, not value inspection. Unknown credential names (for example an application-specific pwd, sig or vendor key header not matching the markers), novel shapes, arbitrary free text and encodings other than complete JSON objects/arrays are outside this policy. Do not put credentials in content fields or metadata. Dictionaries beyond depth 20 are omitted, as are structured strings larger than 1,000,000 characters or unparseable structured strings; opaque objects are not dumped as a fallback.

To disable content capture, set FI_HIDE_INPUTS=true and FI_HIDE_OUTPUTS=true before instrumentation, or pass TraceConfig(hide_inputs=True, hide_outputs=True). Directional text/message hiding also covers CrewAI's content aliases. Wrapper failures record ERROR status without copying exception messages or stacktraces. For manually recorded error events, use FI_HIDE_ERROR_DETAILS=true.

CrewAI's separate native telemetry

CrewAI can export through its own provider to telemetry.crewai.com, independently of traceAI. This instrumentor does not change environment variables, patch CrewAI's telemetry classes, disable its provider or restore/change your settings on uninstrument(). Choose the native telemetry policy explicitly before importing CrewAI.

In CrewAI 0.152.0 and 1.15.33, CREWAI_DISABLE_TELEMETRY=true or CREWAI_DISABLE_TRACKING=true disables native telemetry while leaving traceAI available. OTEL_SDK_DISABLED=true is also honored, but disables the OTel SDK and traceAI spans too; do not use it when you want traceAI tracing. CREWAI_TELEMETRY_OPT_OUT and DO_NOT_TRACK are not native disable flags.

CrewAI 0.41.1 has no native telemetry opt-out flag: its constructor creates an exporter for https://telemetry.crewai.com:4319/v1/traces and ignores the flags above. If you need native telemetry disabled, upgrade to a version that honors CREWAI_DISABLE_TELEMETRY before running sensitive workloads. For legacy workloads, enforce a network egress policy; traceAI's projections cannot protect an independent provider's exports. share_crew=False is not a native telemetry disable switch.

Quickstart

Register Tracer Provider

Set up the trace provider to establish the observability pipeline. The trace provider:

from fi_instrumentation import register
from fi_instrumentation.fi_types import ProjectType

trace_provider = register(
    project_type=ProjectType.OBSERVE,
    project_name="crewai_app"
)

Configure Crewai Instrumentation

Instrument the Crewai client to enable telemetry collection. This step ensures that all interactions with the Crewai SDK are tracked and monitored.

from traceai_crewai import CrewAIInstrumentor

CrewAIInstrumentor().instrument(tracer_provider=trace_provider)

Create Crewai Components

Set up your Crewai client with built-in observability.

from crewai import LLM, Agent, Crew, Process, Task

def story_example():
    llm = LLM(
        model="gpt-4",
        temperature=0.8,
        max_tokens=150,
        top_p=0.9,
        frequency_penalty=0.1,
        presence_penalty=0.1,
        stop=["END"],
        seed=42,
    )

    writer = Agent(
        role="Writer",
        goal="Write creative stories",
        backstory="You are a creative writer with a passion for storytelling",
        allow_delegation=False,
        llm=llm,
    )

    writing_task = Task(
        description="Write a short story about a magical forest",
        agent=writer,
        expected_output="A short story about a magical forest",
    )

    crew = Crew(agents=[writer], tasks=[writing_task])

    # Execute the crew
    result = crew.kickoff()
    print(result)

if __name__ == "__main__":
    story_example()

Metadata

Release files for traceAI-crewai 0.1.10

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for traceAI-crewai 0.1.10
File Size Uploaded Provenance Actions
traceai_crewai-0.1.10.tar.gz 16.4 kB With provenance Details for traceai_crewai-0.1.10.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for traceAI-crewai 0.1.10
File Interpreter ABI Platform Actions
traceai_crewai-0.1.10-py3-none-any.whl Python 3 none any Details for traceai_crewai-0.1.10-py3-none-any.whl

Total release size: 30.8 kB

Release files / traceai_crewai-0.1.10.tar.gz

Download URL traceai_crewai-0.1.10.tar.gz
Size 16.4 kB
Tags Source
SHA-256 checksum
How to use checksums
6c8396282b79c089e947417ce1a490fadae4e094e0f2bb4e834309b6f825ade0
BLAKE2b-256 checksum
How to use checksums
713e8d04c808c49a270ee215cde68b3753da6dddaf5ba87e5baa78796880bec6
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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 Oct 31, 2026.

Transparency log

Release files / traceai_crewai-0.1.10-py3-none-any.whl

Download URL traceai_crewai-0.1.10-py3-none-any.whl
Size 14.4 kB
Tags Python 3
SHA-256 checksum
How to use checksums
9e8507dcfbb1ab330a335d2cae32a66294961dbd8693a1fb95d89bda66a6c4f1
BLAKE2b-256 checksum
How to use checksums
bb1c8df584e1fb6253379152ab0988bf0198a4f42aad6850e20e7aa64cbfe5a5
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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 Oct 31, 2026.

Transparency log

Security for traceAI-crewai 0.1.10

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.

Full provenance

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for traceai_crewai-0.1.10.tar.gz

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 Oct 31, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page