open-claude-cowork
Open Source version of Claude Cowork with 500+ SaaS app integrations
Runs with mockssource: GitHubJavaScriptMITcommit 52335ef50fd0
JavaScript, MIT licensed. The project labels itself: aiagents, anthropic, anthropic claude, claude code, claude cowork, eclectron app, opencode and workflow automation.
open-claude-cowork runs, with stand-ins for the services it depends on. An Argusic agent installed it in 3 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Backend server starts and responds on all API endpoints (health 200, chat 200 with SSE streaming, abort 200, validation errors 400); Electron desktop app launches and prints 'Electron app ready'
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 92 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.
- Composio SDK throws fatal error when COMPOSIO_API_KEY is unset - crashes server startup3 minutes
- Opencode binary not found (spawn opencode ENOENT) - optional provider cannot initialize2 minutes
- Electron SUID sandbox helper not configured in container; dbus not available1 minute
- Install time
- 3 minutes
- Cold machine to finish
- 10 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- curl http://localhost:3001/api/health returned 200; POST /api/chat with 'hello world' returned 200 with mock SSE stream containing session_init, text, and done events; POST with empty message returned 400 'Message is required'; POST with invalid provider returned 400 'Invalid provider: bad'; POST /api/abort returned 200 JSON; Electron --no-sandbox . printed 'Electron app ready' and stayed alive for 10s
- Model tokens used
- 104,704
- Exact commit tested
- 52335ef50fd0
- 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
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
diff -q /work/repo/server/server.js /work/repo/server/server.js.bak 2>/dev/null && echo \"files dif…
# Quick sanity check that the mock produces valid JSON chunks
echo '{\"type\":\"connected\",\"message\":\"test\"}' | node -e \"process.stdin.on('data',d=>console…
succeeded in 0ms:
-rwxrwxr-x 1 runner runner 720434 Sep 30 10:16 /work/repo/server/node_modules/@anthropic-ai/claude-…
-rw-r--r-- 1 runner runner 8323 Sep 30 10:18 /work/repo/server/server.js.bak
files differ (patch applied)
connected
All verified. Here is the complete result.
tokens used
104,704
All verified. Here is the complete result.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
- Installed in 3 minutes.
- Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
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 | 1/3 | Runs with mocks | 92.00 | 0.07 |
Topics (from GitHub)
aiagentsanthropicanthropic-claudeclaude-codeclaude-coworkeclectron-appopencodeworkflow-automation
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/open-claude-cowork)Questions
- Does open-claude-cowork run?
- open-claude-cowork runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 3 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test open-claude-cowork?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 52335ef50fd0. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test open-claude-cowork?
- The run that produced this verdict cost $0.07: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does open-claude-cowork take to install?
- 3 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 open-claude-cowork need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing open-claude-cowork?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for open-claude-cowork?
- 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.