kaogong-shuati
考公刷题 App（公考/gongkao/国考/省考/事业单位）：行测 申论 题库 · 错题本 · AI 解析。中文名：没钱考什么公。
Runssource: GitHubJavaScriptMITcommit 12cf8e73be8f
JavaScript, MIT licensed. The project labels itself: ai, android, capacitor, civil service exam, education, exam prep, gongkao and kaogong.
kaogong-shuati runs. An Argusic agent installed it in 8 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Server launches on Node.js v22.6.0 with --experimental-sqlite flag, serves all API endpoints, passes 121/130 tests (106 pass without patches, 15 more pass after spawn patches)
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. 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.
- Node.js v18.19.1 (system) does not support node:sqlite; project requires >=22.52 minutes
- test-custom-practice-e2e.mjs used playwright msedge channel which was not installed2 minutes
- node:sqlite requires --experimental-sqlite flag in v22.6.01 minute
- Tests spawning child server (test-random-practice-count.mjs et al.) did not pass --experimental-sqlite flag1 minute
- test-local-api.mjs, test-local-queries.mjs, test-local-ai.mjs fail because app-assets/tiku_app.db does not exist
- Install time
- 8 minutes
- Cold machine to finish
- 8 minutes
- Errors hit and fixed
- 5 hit, 5 fixed with no human help
- How the result was proved
- node --experimental-sqlite server.mjs 3099: / returns 200 (5526 bytes HTML), /api/subjects returns 4 subjects (31643 questions), /api/practice returns real questions, /api/ai/agents returns 4 agents, /api/records/stats returns practice stats, /api/favorites CRUD works
- Model tokens used
- 197,911
- Exact commit tested
- 12cf8e73be8f
- 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.
exec /bin/sh -lc 'kill %1 2>/dev/null; true' in /work/repo succeeded in 0ms: Now let me compile the final ARGUSIC_RESULT. Let me re-check the precision of the install time: exec /bin/sh -lc 'date +%s' in /work/repo succeeded in 0ms: 1794296588 The process started around 1794296100 (07:35) and now at 1794296588 (07:43) — ~8 minutes. tokens used 197,911 The process started around 1794296100 (07:35) and now at 1794296588 (07:43) — ~8 minutes.
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 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 MIT, as reported by its host.
What did not, or is not known
- Took 8 minutes to install, slower than the median of the 232 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 233 ai projects Argusic has installed and timed, kaogong-shuati was the 143rd fastest to reach a running state, and 156 of 233 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 8 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)
aiandroidcapacitorcivil-service-exameducationexam-prepgongkaokaogongllmlocal-firstnodejsoffline-firstpwaquestion-bankself-hostedshenlunshuatisqlitestudy-appxingce
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/kaogong-shuati)Questions
- Does kaogong-shuati run?
- Yes. kaogong-shuati runs. Argusic installed and launched it on a clean machine in 8 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test kaogong-shuati?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 12cf8e73be8f. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test kaogong-shuati?
- The run that produced this verdict cost $0.22: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does kaogong-shuati take to install?
- 8 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 kaogong-shuati need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing kaogong-shuati?
- 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 kaogong-shuati compare with the alternatives?
- Of the 233 ai projects Argusic has installed and timed, kaogong-shuati was the 143rd fastest to reach a running state, and 156 of 233 reached one at all.
- Where is the evidence for kaogong-shuati?
- 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.