Skip to main content

lookspan-crewai — CrewAI observability, local-first

PyPI License: MIT Docs

Auto-instruments CrewAI runs and streams every agent step, task, tool call, and LLM invocation to your local Lookspan dashboard — a process on 127.0.0.1, not a SaaS. No account, no API key, nothing uploaded.

A crew that "just hangs" or burns tokens somewhere is hard to read from logs. Here you get the kickoff as a trace, each agent and task as a span, and the tool and LLM calls nested underneath with their real durations.

Install

pip install lookspan-crewai

Quick start

from crewai import Crew
from lookspan import LookspanClient
from lookspan_crewai import attach_lookspan

client = LookspanClient(endpoint="http://127.0.0.1:3100/api/ingest")
attach_lookspan(client, agent_id="research-crew")

crew = Crew(agents=[...], tasks=[...])
result = crew.kickoff()

client.flush()

attach_lookspan registers listeners on CrewAI's global event bus.

Prompts and completions are not recorded unless you pass capture_content=True to LookspanClient.

Links

MIT licensed. Part of Fervon.

Metadata

Release files for lookspan-crewai 0.5.3

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

Source distribution (sdist)

Source distribution for lookspan-crewai 0.5.3
File Size Uploaded Provenance
lookspan_crewai-0.5.3.tar.gz 6.0 kB With provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for lookspan-crewai 0.5.3
File Interpreter ABI Platform
lookspan_crewai-0.5.3-py3-none-any.whl Python 3 none any Details

Total release size: 10.8 kB

Release files / lookspan_crewai-0.5.3.tar.gz

Download URL lookspan_crewai-0.5.3.tar.gz
Size 6.0 kB
Tags Source
SHA-256 checksum
How to use checksums
992644bef6672e2df80c8a38b863f23ab8e28986f2da6803d7868e9db17cbf5f
BLAKE2b-256 checksum
How to use checksums
2cc90fbaaec8913608c19fc9cd0bde578dfe022da8aadcb15d1ca9b624f819c1
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 Aug 19, 2026.

Transparency log

Release files / lookspan_crewai-0.5.3-py3-none-any.whl

Download URL lookspan_crewai-0.5.3-py3-none-any.whl
Size 4.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
e50d3546fb68822e0b599650b14750647298d8be3e17d61883af36155b689f92
BLAKE2b-256 checksum
How to use checksums
affd71762b7c6b67eb7eaa95d9cfa715d2172306d9751facc6fd17c4e7810750
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 Aug 19, 2026.

Transparency log

Security for lookspan-crewai 0.5.3

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

All 2 files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for lookspan_crewai-0.5.3.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 Aug 19, 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