zhikuncode
Codex/Claude Code/Cursor的开源增强版，专注一句话实现复杂长程任务（教育、编程、办公、生活、娱乐、游戏）。部署在你自己的服务器上，团队用浏览器打开就能编程, 包括手机。CLI & Web UI 双入口，Multi-Agent 协作，原生直连千问/DeepSeek 等国产大模型。技能/插件/跨会话记忆，8 层安全沙箱，数据不离开你的机器。Docker 一键部署，MIT 开源，零锁定。
Runssource: GitHubhomepageJavaMITcommit 0d39e2ddb966
Java, MIT licensed. The project labels itself: ai coding assistant, chinese llm, docker, llm, multi agent, open source, self hosted and web ui.
zhikuncode runs. An Argusic agent installed it in 21 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Python FastAPI service runs on port 8000 with health endpoint OK; Java Spring Boot backend runs on port 8080 with actuator health status UP and SQLite global+project databases operational; React frontend builds cleanly with 207/223 tests passing; all three tiers (Python 105/107, Java 2392/2454, React 207/223) pass their test suites.
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.
- jsdom@29 requires Node >=20 (container has 18); ESM-only @exodus/bytes cannot be require()d3 minutes
- No JDK 21 available in container (no root)3 minutes
- Missing Python dependency: jsonpath-ng1 minute
- Log4j2 could not create /work/log directory (relative path ../log resolved outside repo)
- Install time
- 21 minutes
- Cold machine to finish
- 18 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- Python: curl http://127.0.0.1:8000/api/health returned 200 with status=ok and version=1.15.0; Backend: curl http://localhost:8080/actuator/health returned 200 with status=UP and SQLite databases healthy; Backend unit tests: 2392 passed 0 failed 62 skipped BUILD SUCCESS; Frontend unit tests: 207 passed 16 skipped; Frontend build: npm run build produced dist/index.html; Python unit tests: 105 passed 2 skipped
- Model tokens used
- 90,851
- Exact commit tested
- 0d39e2ddb966
- 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 1, run . The verdict above comes from a different attempt, so read this as one session and not as the current result. 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.
tokens used 90,851 Here's a summary of what was done: ## Errors encountered and fixes 1. **Missing Python dep `jsonpath-ng`**: `src/routers/http_api.py` imports it but it wasn't in `pyp… 2. **jsdom@29 ESM incompatibility with Node 18**: The pinned `jsdom@29` depends on `@exodus/bytes` … 3. **No JDK 21 in container**: No `sudo` access to install packages. Fixed by downloading Adoptium … 4. **Log4j2 `LOG_DIR=../log` resolves outside `/work/repo`**: The relative path `../log` resolves t… ## What works - **Python service** (port 8000): `curl /api/health` → `200`, `status=ok`, `version=1.15.0`. Tests:… - **Java backend** (port 8080): `curl /actuator/health` → `200`, `status=UP` with SQLite global+pro… - **React frontend**: Tests **207 passed, 16 skipped**. Production build creates `dist/index.html`.
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 21 minutes to install, slower than the median of the 3 comparable projects Argusic has measured.
Of the 4 ai-coding-assistant projects Argusic has installed and timed, zhikuncode was the 4th fastest to reach a running state, and 4 of 4 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
Topics (from GitHub)
ai-coding-assistantchinese-llmdockerllmmulti-agentopen-sourceself-hostedweb-ui
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/zhikuncode)Questions
- Does zhikuncode run?
- Yes. zhikuncode runs. Argusic installed and launched it on a clean machine in 21 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test zhikuncode?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 0d39e2ddb966. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test zhikuncode?
- 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 zhikuncode take to install?
- 21 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 zhikuncode need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing zhikuncode?
- 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 zhikuncode compare with the alternatives?
- Of the 4 ai-coding-assistant projects Argusic has installed and timed, zhikuncode was the 4th fastest to reach a running state, and 4 of 4 reached one at all.
- Where is the evidence for zhikuncode?
- 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.