opencrew

Openclaw多智能体协同系统 | Multi-Agent OS for Decision Makers, 基于 OpenClaw (Clawbot) + Slack,让 AI 团队各司其职、自主稳定迭代。

Runssource: GitHubShellMITcommit 7937758b7016

Shell, MIT licensed. The project labels itself: a2a protocol, agent deployment, agent orchestration, ai agents, ai assistant, ai productivity, ai team and autonomous agents.

opencrew runs. An Argusic agent installed it in 14 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

OpenClaw 2026.10.5 gateway runs with 7 OpenCrew agents (main, cos, cto, builder, ko, ops, research) and real OpenRouter model inference works

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 100 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs
Argusic Score
100 / 100
cost of the verifying run
$0.05 (measured)
recorded runs
1
last tested
stars
498
forks
70
open issues
11
watchers
4
size
3 MB
created
last push

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.

Time lost to each failure while testing opencrew, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • Node 18.19.1 is too old - openclaw requires >=24.16.03 minutes
  • npm install -g failed EACCES1 minute
  • Config validation: agents.ownership required for multi-agent, session.agentToAgent unrecognized1 minute
  • OpenRouter API key has insufficient credits for gpt-6-astra (needs 128k tokens)1 minute
Install time
14 minutes
Cold machine to finish
13 minutes
Errors hit and fixed
4 hit, 4 fixed with no human help
How the result was proved
openclaw agent exec --model openrouter/openai/gpt-5.6-luna succeeded with response 'OpenCrew turns OpenClaw into a manageable multi-agent AI team...' and a second exec listing all 9 shared protocol files correctly
Model tokens used
484,253
Exact commit tested
7937758b7016
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.

484,253
OpenCrew is deployed and verified. Here's the summary:
**Install & Deploy:**
- Installed Node 24.16.0 via nvm (needed by [email protected])
- Installed OpenClaw globally
- Created config with 7 agents (main, cos, cto, builder, ko, ops, research)
- Copied all shared protocol files and workspace files to `~/.openclaw/`
- Gateway starts successfully with all 7 agents
**Verification:**
- `openclaw agent exec --model Argusic/openai/gpt-5.6-luna --timeout 60` answered correctly: "OpenC…
- Second turn also succeeded, listing all 9 shared files and their purposes
- Gateway status confirms 7 agents with routing rules configured

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.
  • Installed in 14 minutes.
  • Recovered from all 4 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.

What did not, or is not known

  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

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 byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs100.000.05

Topics (from GitHub)

a2a-protocolagent-deploymentagent-orchestrationai-agentsai-assistantai-productivityai-teamautonomous-agentsclawdbotcontext-managementknowledge-managementllmmulti-agentno-codeopenclawsession-managementslackslack-botteam-managementworkflow-automation

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/opencrew.svg)](https://argusic.com/subject/opencrew)

Questions

Does opencrew run?
Yes. opencrew runs. Argusic installed and launched it on a clean machine in 14 minutes, hitting 4 errors on the way, and recorded the session.
How did Argusic test opencrew?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 7937758b7016. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test opencrew?
The run that produced this verdict cost $0.05: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does opencrew take to install?
14 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 opencrew need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing opencrew?
4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
Where is the evidence for opencrew?
The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion