Yes. ponzu runs. Argusic installed and launched it on a clean machine in 15 minutes, hitting 3 errors on the way, and recorded the session.

How did Argusic test ponzu?

On a fresh, disposable machine, with every command recorded and the repository pinned at commit 5c57b559e76b. One attempt is recorded, and the full method is on the methodology page.

What did it cost to test ponzu?

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 ponzu take to install?

15 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 ponzu need a GPU?

Not to start. Argusic reached a running state on a machine with no GPU.

What goes wrong when installing ponzu?

3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.

Where is the evidence for ponzu?

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.

ponzu

Headless CMS with automatic JSON API. Featuring auto-HTTPS from Let's Encrypt, HTTP/2 Server Push, and flexible server framework written in Go.

Runssource: GitHub homepageGoBSD-3-Clausecommit 5c57b559e76b

Go, BSD-3-Clause licensed. The project labels itself: api, cli, cms, golang, http2, json, productivity and server.

ponzu runs. An Argusic agent installed it in 15 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Ponzu v0.11.0 builds and runs from the repo root: ponzu CLI shows version, the HTTP server starts and responds on /admin/init (200), /admin/login (302), /api/contents?type=Review (200), and /api/search (400), the core HTTP API and admin system are operational.
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

verdict: Runs
Argusic Score: 100 / 100
cost of the verifying run: $0.09 (measured)
recorded runs: 1
last tested: 2026-09-29
stars: 5,760
forks: 384
open issues: 35
watchers: 128
size: 4 MB
created: 2016-09-17
last push: 2025-11-17

Subject data from GitHub, linked at the top of this page, refreshed 2026-09-30. 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.

Time lost to each failure while testing ponzu, drawn from the recorded run — Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

GOPATH-mode go get failed on modern Go; no go.mod found3 minutes
golang.org/x/crypto v0.57.0 requires go 1.26+; building with go 1.22.103 minutes
Go (1.22+) not installed2 minutes

Install time: 15 minutes
Cold machine to finish: 17 minutes
Errors hit and fixed: 3 hit, 3 fixed with no human help
How the result was proved: go build ./cmd/ponzu/ exited 0; ./ponzu serve admin,api --port=8081 started; curl -o /dev/null -w '%{http_code}' http://localhost:8081/admin/init returned 200; curl -o /dev/null -w '%{http_code}' 'http://localhost:8081/api/contents?type=Review' returned 200 with body {"data":[]}
Model tokens used: 293,364
Exact commit tested: 5c57b559e76b
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.

- `GET /api/contents?type=Review` returned **200** with `{"data":[]}`
- Content generation (`ponzu gen content review ...`) works and creates valid Go types
**Pre-existing test issues (not fixed, not mine):**
- `TestParseType` fails because template path assumes being inside a project dir
- `TestNewName2Path` fails because test fixtures directory is missing
- Two name/field tests (`TestFieldJSONName`, `TestFieldName`) pass
**Errors encountered:**
| Error | Fix | Time |
|---|---|---|
| Go not installed | Downloaded Go 1.22.10 tarball, extracted | ~2 min |
| GOPATH mode broken with modern Go | Created go.mod and used module mode | ~3 min |
| `golang.org/x/crypto v0.57.0` requires go ≥ 1.26 | Downgraded crypto, net, text, sys deps | ~3 mi…

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 15 minutes, faster than the median of the 6 comparable projects Argusic has measured.
Recovered from all 3 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.

What did not, or is not known

Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 7 api projects Argusic has installed and timed, ponzu was the 4th fastest to reach a running state, and 4 of 7 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

tested by	attempt	outcome	score	cost USD	when
Argusic Runner	1/3	Runs	100.00	0.09	2026-09-29 13:32 UTC

Topics (from GitHub)

api cli cms golang http2 json productivity server tls

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/ponzu.svg)](https://argusic.com/subject/ponzu)

Questions

Does ponzu run?: Yes. ponzu runs. Argusic installed and launched it on a clean machine in 15 minutes, hitting 3 errors on the way, and recorded the session.
How did Argusic test ponzu?: On a fresh, disposable machine, with every command recorded and the repository pinned at commit 5c57b559e76b. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test ponzu?: 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 ponzu take to install?: 15 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 ponzu need a GPU?: Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing ponzu?: 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does ponzu compare with the alternatives?: Of the 7 api projects Argusic has installed and timed, ponzu was the 4th fastest to reach a running state, and 4 of 7 reached one at all.
Where is the evidence for ponzu?: 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.