CPA-Manager-Plus
A self-hosted CPA / CLIProxyAPI management panel and AI gateway observability dashboard for requests, usage, cost, quota, failures, and account health.
Runssource: GitHubhomepageGoMITcommit eea422fd6a19
Go, MIT licensed. The project labels itself: ai gateway, claude code, cliproxyapi, codex, cost analysis, cpa, gateway monitoring and observability.
CPA-Manager-Plus runs. An Argusic agent installed it in 21 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
CPA Manager Plus web app builds to a single-file index.html, Go manager server compiles and listens on :18317 with /health returning 200, all 4156 frontend and all Go backend tests pass without errors.
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.
- Node.js v18.19.1 in container is too old for Vite 8 (requires ^20.19.0 or >=22.12.0). npm install succeeded with engine warnings but vite commands crashed with ReferenceError: CustomEvent is not defined. Go toolchain was also missing.5 minutes
- Install time
- 21 minutes
- Cold machine to finish
- 24 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- npm run test:web exited 0 (252 files, 4156 passed); npm run test:repo exited 1 (1 env-only failure, 256 passed); go test -race ./... exited 0 (all packages OK); go vet ./... exited 0; curl http://localhost:18317/health returned {"ok":true,"service":"cpa-manager-plus"}; npm run build produced dist/index.html (6.4 MB); npm run docs:build completed in 6s
- Model tokens used
- 143,491
- Exact commit tested
- eea422fd6a19
- 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.
[plugin vite:singlefile] Inlining: style-B1ulpjyy.css computing gzip size... dist/index.html 6,410.65 kB │ gzip: 1,738.42 kB ✓ built in 5.04s Build succeeded. Everything is verified. Here is my final report: All components install cleanly and pass their tests. No mocks were needed — the project is self-con… **Node.js upgrade**: The container had Node 18.19.1, which Vite 8 rejects. Downloaded Node 22.14.0 … tokens used 143,491 Build succeeded. Everything is verified. Here is my final report: All components install cleanly and pass their tests. No mocks were needed — the project is self-con… **Node.js upgrade**: The container had Node 18.19.1, which Vite 8 rejects. Downloaded Node 22.14.0 …
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 1 error 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 22 comparable projects Argusic has measured.
Of the 23 ai-gateway projects Argusic has installed and timed, CPA-Manager-Plus was the 16th fastest to reach a running state, and 17 of 23 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-gatewayclaude-codecliproxyapicodexcost-analysiscpagateway-monitoringobservabilityopenaiopenai-compatiblequota-managementrequest-monitoringusage-tracking
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/cpa-manager-plus)Questions
- Does CPA-Manager-Plus run?
- Yes. CPA-Manager-Plus runs. Argusic installed and launched it on a clean machine in 21 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test CPA-Manager-Plus?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit eea422fd6a19. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test CPA-Manager-Plus?
- The run that produced this verdict cost $0.11: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does CPA-Manager-Plus 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 CPA-Manager-Plus need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing CPA-Manager-Plus?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does CPA-Manager-Plus compare with the alternatives?
- Of the 23 ai-gateway projects Argusic has installed and timed, CPA-Manager-Plus was the 16th fastest to reach a running state, and 17 of 23 reached one at all.
- Where is the evidence for CPA-Manager-Plus?
- 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.