deepseek-harness-desktop
Open-source Windows desktop client and GUI for DeepSeek Harness, zero-setup installer with Codex, plugins, skills, SSH, mobile remote access, and 11 skins.
Runssource: GitHubhomepageJavaScriptBSD-3-Clausecommit e6c6756cf14b
JavaScript, BSD-3-Clause licensed. The project labels itself: ai agent, ai coding assistant, codex, deepseek, deepseek harness, desktop app, dsh and dsh plugin.
deepseek-harness-desktop runs. An Argusic agent installed it in 5 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Dependencies installed, all 40 workspace projects build and typecheck. Script tests 200/200 pass. Desktop test suite 1229/1229 pass (0 fail, 26 skipped). DSH web runtime starts and serves HTTP (401 with auth active). One pre-existing issue: dsh-ssh engine.test.ts needs ssh-keygen (openssh-client) unavailable in this container; 14/15 dsh-ssh test suites 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 98.3 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.
- dsh-desktop integration test fails: Playwright browsers not installed2 minutes
- Node.js v18.19.1 is below the project's requirement (^22.19.0)1 minute
- pnpm not found in PATH1 minute
- dsh-ssh prepare failed due to packageManager field declaring [email protected] while corepack runs 11.22.01 minute
- dsh-ssh engine.test.ts: spawnSync ssh-keygen ENOENT
- Install time
- 5 minutes
- Cold machine to finish
- 22 minutes
- Errors hit and fixed
- 5 hit, 5 fixed with no human help
- How the result was proved
- pnpm -r build exited 0 (40/40 projects). pnpm typecheck exited 0. pnpm test:scripts exited 0 (200/200 tests pass). pnpm --filter @linxin666/dsh-desktop test: 1255 tests, 1229 pass, 0 fail. DSH web profile launched: curl to port returned HTTP 401 as expected (token auth active).
- Model tokens used
- 102,342
- Exact commit tested
- e6c6756cf14b
- 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
Watch the session
The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.
A recording of attempt 2, run , the attempt that decided the verdict above. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
# fail 0
Now I have all the data. Let me compile the final report
exec
/bin/sh -lc 'export PATH="/home/runner/node-v22.19.0-linux-x64/bin:$PATH" && cd /work/repo && pnpm …
succeeded in 8287ms:
SCRIPTS_EXIT:0
Here's my final report:
**ARGUSIC_RESULT:** {"install_succeeded":true,"launch_succeeded":true,"install_minutes":5,"errors":…
tokens used
102,342
Here's my final report:
**ARGUSIC_RESULT:** {"install_succeeded":true,"launch_succeeded":true,"install_minutes":5,"errors":…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 5 minutes, faster than the median of the 11 comparable projects Argusic has measured.
- 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 BSD-3-Clause, as reported by its host.
- Measured 2 times, so the result is not a one-off.
Of the 12 ai-agent projects Argusic has installed and timed, deepseek-harness-desktop was the 6th fastest to reach a running state, and 9 of 12 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 5 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)
ai-agentai-coding-assistantcodexdeepseekdeepseek-harnessdesktop-appdshdsh-pluginelectronelectron-appguiopen-sourceplugin-systempluginsremote-accessskillsssh-clientwindowswindows-desktop
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/deepseek-harness-desktop)Questions
- Does deepseek-harness-desktop run?
- Yes. deepseek-harness-desktop runs. Argusic installed and launched it on a clean machine in 5 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test deepseek-harness-desktop?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit e6c6756cf14b. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test deepseek-harness-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 deepseek-harness-desktop take to install?
- 5 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 deepseek-harness-desktop need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing deepseek-harness-desktop?
- 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 deepseek-harness-desktop compare with the alternatives?
- Of the 12 ai-agent projects Argusic has installed and timed, deepseek-harness-desktop was the 6th fastest to reach a running state, and 9 of 12 reached one at all.
- Where is the evidence for deepseek-harness-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.