APIPark
Cloud native, ultra-high performance AI&API gateway, LLM API management, distribution system, open platform, supporting all AI APIs.🦄云原生、超高性能 AI&API网关，LLM API 管理、分发系统、开放平台，支持所有AI API，不限于OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型，统一 API 请求和返回，API申请与审批，调用统计、负载均衡、多模型灾备。一键部署，开箱即用。
Runs with mockssource: GitHubhomepageTypeScriptApache-2.0commit b6b58db20bfb
TypeScript, Apache-2.0 licensed. The project labels itself: ai, ai gateway, api, api gateway, api platform, api portal, apihub and claude.
APIPark runs, with stand-ins for the services it depends on. An Argusic agent installed it in 14.5 minutes and hit 6 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
APIPark binary builds, starts on port 8288 with MySQL and Redis, serves HTTP 200 JSON API responses and embedded index.html, auto-creates all database tables, and passes 4 test packages.
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 92 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.
- MySQL 8.0 gets OOM-killed on 2GB RAM (requires ~400MB RSS)5 minutes
- libaio.so.1 not found - MySQL 8.0.37 required library missing2 minutes
- Go not found in container1.5 minutes
- Frontend dist/ directory missing (required by go:embed directive)1 minute
- log-driver/loki/loki_test.go: NewDriver returns 3 values but test expects 2
- ai-provider/local/executor_test.go: TestPullModel times out after 60s (starts HTTP server)
- Install time
- 15 minutes
- Cold machine to finish
- 57 minutes
- Errors hit and fixed
- 6 hit, 6 fixed with no human help
- How the result was proved
- curl http://127.0.0.1:8288/ returned HTTP 200; curl http://127.0.0.1:8288/api/v1/account/login returned HTTP 200 with JSON '{"data":{"channel":[{"name":"username"}],"status":"anonymous"},"code":0,"success":"success"}'; go test on resources/access (PASS, 0.023s), module/ai-api (PASS, 0.161s), module/system/dto (PASS, 0.002s), ai-provider/model-runtime (PASS, 0.182s)
- Model tokens used
- 722,614
- Exact commit tested
- b6b58db20bfb
- 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
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
--- PASS: TestPrintlnRoleAccess (0.00s) --- PASS: TestPrintlnAccessAPIs (0.00s) --- PASS: TestPrintName (0.00s) ok github.com/APIParkLab/APIPark/resources/access 0.023s --- PASS: TestSchemaBuild (0.00s) ok github.com/APIParkLab/APIPark/module/ai-api 0.161s --- PASS: TestMap (0.00s) ok github.com/APIParkLab/APIPark/module/system/dto 0.003s --- PASS: TestLoad (0.09s) ok github.com/APIParkLab/APIPark/ai-provider/model-runtime 0.182s tokens used 722,614
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
- Recovered from all 6 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed Apache-2.0, as reported by its host.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Took 14.5 minutes to install, slower than the median of the 92 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 93 ai projects Argusic has installed and timed, APIPark was the 72nd fastest to reach a running state, and 64 of 93 reached one at all.
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 | 1/3 | Runs with mocks | 92.00 | 0.23 |
Topics (from GitHub)
aiai-gatewayapiapi-gatewayapi-platformapi-portalapihubclaudedeepseekdeveloper-portalgatewayllm-gatewayopenaiqwen
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/apipark)Questions
- Does APIPark run?
- APIPark runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 15 minutes, hitting 6 errors on the way, and recorded the session.
- How did Argusic test APIPark?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit b6b58db20bfb. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test APIPark?
- The run that produced this verdict cost $0.23: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does APIPark take to install?
- 14.5 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 APIPark need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing APIPark?
- 6 things broke in the recorded run, and 6 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does APIPark compare with the alternatives?
- Of the 93 ai projects Argusic has installed and timed, APIPark was the 72nd fastest to reach a running state, and 64 of 93 reached one at all.
- Where is the evidence for APIPark?
- 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.