SoduWork
The AI-native engine for teams and their agents. Multi-harness, multi-agent, self-hosted.
Runssource: GitHubhomepageJavaScriptMITcommit 5dd7fd91caea
JavaScript, MIT licensed. The project labels itself: agent harness, agent orchestration, agent workflows, ai agents, ai workflows, anti slop, claude code and codex.
SoduWork runs. An Argusic agent installed it in 2 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
SoduWork hub service starts on port 18989 with initial admin account, management UI serves, API supports login/auth, organization/task CRUD, and attachment upload/download; Electron desktop launches on Xvfb display :99 and connects to the local hub.
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
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.
- Electron sandbox fails in container (need SUID chrome-sandbox owned by root with mode 4755)3 minutes
- Node.js v18.19.1 provided by Ubuntu 24.04 but the project requires v22.19+2 minutes
- Install time
- 2 minutes
- Cold machine to finish
- 14 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- python3 tools/dev/verify_local_start.py --desktop returned {"ok": true, "checks": ["failed-first-password-resumes", "clean-venv-npm-build-migrations-ready", "native-electron-ready-with-isolated-local-hub-profile", "built-management-ui-and-assets", "source-runner-download-has-dependencies-and-agent-catalog", "actual-password-login-and-auth-rejection", "organization-and-task-http-create-read-update", "real-attachment-upload-download", "duplicate-launch-does-not-disrupt-service", "ctrl-c-reaps-hub-and-releases-port", "restart-preserves-account-login-token-task-attachment-and-build-cache", "no-admin-password-or-token-written-to-config-or-logs", "electron-stopped-after-ctrl-c-and-killed-launcher", "closed-launcher-pipe-stops-orphan-hub"]}
- Model tokens used
- 180,170
- Exact commit tested
- 5dd7fd91caea
- 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 '# Check the server we started is still running pgrep -f "_soduwork_source_server" 2>/dev/null || echo "Not running (expected, verify script stoppe… succeeded in 0ms: 8462 There's still a lingering server process from the test. Let me clean that up. exec /bin/sh -lc 'kill $(pgrep -f "_soduwork_source_server" 2>/dev/null) 2>/dev/null || true' in /work/r… exited 143 in 0ms: Now let me summarize what was done. tokens used 180,170 Now let me summarize what was done.
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 2 minutes, faster than the median of the 10 comparable projects Argusic has measured.
- Recovered from all 2 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.
Of the 11 agent-harness projects Argusic has installed and timed, SoduWork was the 3rd fastest to reach a running state, and 8 of 11 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.
- A quick evaluation: it was running 2 minutes after the clone.
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
Topics (from GitHub)
agent-harnessagent-orchestrationagent-workflowsai-agentsai-workflowsanti-slopclaude-codecodexdeepseekelectronfastapiharnesshuman-in-the-loopllmmcpmulti-agentopencodeplugin-systemself-hostedteam-collaboration
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/soduwork)Questions
- Does SoduWork run?
- Yes. SoduWork runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test SoduWork?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 5dd7fd91caea. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test SoduWork?
- The run that produced this verdict cost $0.12: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does SoduWork take to install?
- 2 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 SoduWork need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing SoduWork?
- 2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does SoduWork compare with the alternatives?
- Of the 11 agent-harness projects Argusic has installed and timed, SoduWork was the 3rd fastest to reach a running state, and 8 of 11 reached one at all.
- Where is the evidence for SoduWork?
- 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.