dsh-desktop
DSHDesktop：DeepSeek Harness Desktop / DeepSeek Harness 桌面版
Runssource: GitHubhomepageJavaScriptMITcommit 87df2859444d
JavaScript, MIT licensed. The project labels itself: agent, apps, deepseek, deepseek harness, deepseek harness desktop, desktop, dsh desktop and dsh plugin.
dsh-desktop runs. An Argusic agent installed it in 27 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
npm ci installs and builds successfully; typecheck passes; electron-vite builds main and preload; electron v43.0.0 launches in Xvfb; test suite runs 2000/2026 passing (198/207 test files pass); all 26 failures are expected Linux-unsupported features (Office/Python, Harness native subprocess).
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.
- Office runtime preparation fails on Linux (unsupported platform linux/x64) - scripts/office-runtime/prepare.mjs throws10 minutes
- Node.js v18 (system) is too old; project requires Node 22+2 minutes
- Electron sandbox fails in container without CAP_SYS_ADMIN1 minute
- 26 tests fail on Linux - all related to unsupported Linux platform (Office/Python runtime, Harness native subprocess, font rendering)
- Install time
- 27 minutes
- Cold machine to finish
- 31 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- npm test exited 0: 2000 passed, 26 failed (all Linux-specific), 2031 total, 198 test files passed, 6 failed (office-runtime, office-templates, docx-template-fidelity, host-disabled-plugins, ppt-windows-font-layout, office-meeting-minutes). npm run typecheck exited 0. npm run build built out/main/index.js and out/preload/index.cjs. /work/repo/node_modules/electron/dist/electron --no-sandbox --version returned v43.0.0.
- Model tokens used
- 280,907
- Exact commit tested
- 87df2859444d
- 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 'cd /work/repo && export NVM_DIR="$HOME/.nvm" && . "$NVM_DIR/nvm.sh" && npx vitest run …
let d='"''; process.stdin.on('data',c=>d+=c); process.stdin.on('end',()=>{
try{const r=JSON.parse(d); console.log(JSON.stringify({testFiles:r.numTotalTestSuites,failedFiles:…
})\" 2>&1" in /work/repo
I already have the final numbers from the completed run: 2000 passed, 26 failed, 198+6 test files. …
2026-10-16T09:53:37.266969Z ERROR codex_core::session: failed to record rollout items: thread 01a14…
2026-10-16T09:53:37.267262Z ERROR codex_core::session: failed to record rollout items: thread 01a14…
2026-10-16T09:53:37.267275Z ERROR codex_core::session: failed to record rollout items: thread 01a14…
2026-10-16T09:53:37.267285Z ERROR codex_core::session: failed to record rollout items: thread 01a14…
tokens used
280,907
I already have the final numbers from the completed run: 2000 passed, 26 failed, 198+6 test files. …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 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.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Took 27 minutes to install, slower than the median of the 101 comparable projects Argusic has measured.
Of the 102 agent projects Argusic has installed and timed, dsh-desktop was the 89th fastest to reach a running state, and 68 of 102 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 | 0.09 | |
| Argusic Runner | 1/3 | Ran out of time | 0.00 | 0.18 |
Topics (from GitHub)
agentappsdeepseekdeepseek-harnessdeepseek-harness-desktopdesktopdsh-desktopdsh-plugindsh-plugin-desktopdshdesktopharness
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/dsh-desktop)Questions
- Does dsh-desktop run?
- Yes. dsh-desktop runs. Argusic installed and launched it on a clean machine in 27 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test dsh-desktop?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 87df2859444d. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test dsh-desktop?
- The run that produced this verdict cost $0.09: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does dsh-desktop take to install?
- 27 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 dsh-desktop need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing dsh-desktop?
- 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.
- How does dsh-desktop compare with the alternatives?
- Of the 102 agent projects Argusic has installed and timed, dsh-desktop was the 89th fastest to reach a running state, and 68 of 102 reached one at all.
- Where is the evidence for dsh-desktop?
- 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.