crewAI
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
Runssource: GitHubhomepagePythonMITcommit dd4a10629133
Python, MIT licensed. The project labels itself: agents, ai, ai agents, aiagentframework and llms.
crewAI runs. An Argusic agent installed it in 15 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
CrewAI v1.15.22 is installed with all optional extras, the CLI reports version 1.15.22, and 5424 of 5427 crewai tests pass (3 pre-existing unrelated failures), 87 crewai-core tests pass, 489 crewai-tools tests pass.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 60 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- boto3, google-genai, azure SDKs not installed3 minutes
- uv not installed in environment2 minutes
- a2a-sdk not installed (ModuleNotFoundError: a2a)1 minute
- anthropic SDK not installed (ModuleNotFoundError: anthropic)1 minute
- qdrant-client not installed (ModuleNotFoundError: qdrant_client)1 minute
- Install time
- 15 minutes
- Cold machine to finish
- 59 minutes
- Errors hit and fixed
- 5 hit, 5 fixed with no human help
- How the result was proved
- uv run crewai --version returned 'crewai, version 1.15.22'; uv run pytest lib/crewai/tests/ returned 5424 passed, 3 failed, 62 skipped in 106s; uv run pytest lib/crewai-core/tests/ returned 87 passed; uv run pytest lib/crewai-tools/tests/ returned 489 passed, 2 skipped; Python imports of Crew, Agent, Task, Process, Flow all succeeded
- Model tokens used
- 617,372
- Exact commit tested
- dd4a10629133
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
/bin/sh -lc 'export PATH="$HOME/.local/bin:$PATH" && cd /work/repo && uv run pytest lib/crewai-tool… succeeded in 10517ms: -- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html 489 passed, 2 skipped, 82 warnings in 6.93s exec /bin/sh -lc 'export PATH="$HOME/.local/bin:$PATH" && cd /work/repo && uv run crewai --version 2>&1'… succeeded in 212ms: crewai, version 1.15.22 All verified. Here's the final report: tokens used 617,372 All verified. Here's the final report:
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Recovered from all 5 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Took 15 minutes to install, slower than the median of the 8 comparable projects Argusic has measured.
Of the 9 agents projects Argusic has installed and timed, crewAI was the 9th fastest to reach a running state, and 6 of 9 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs | 100.00 | 0.17 | |
| Argusic Runner | 1/3 | Did not run | 20.00 | 0.07 |
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/crewai)Questions
- Does crewAI run?
- Yes. crewAI runs. Argusic installed and launched it on a clean machine in 15 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test crewAI?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit dd4a10629133. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test crewAI?
- The run that produced this verdict cost $0.17: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does crewAI take to install?
- 15 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does crewAI need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing crewAI?
- 5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does crewAI compare with the alternatives?
- Of the 9 agents projects Argusic has installed and timed, crewAI was the 9th fastest to reach a running state, and 6 of 9 reached one at all.
- Where is the evidence for crewAI?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.