Yes. harlequin runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 1 error on the way, and recorded the session.

How did Argusic test harlequin?

On a fresh, disposable machine, with every command recorded and the repository pinned at commit 5c463bf8b29e. 2 attempts are recorded, and the full method is on the methodology page.

What did it cost to test harlequin?

The run that produced this verdict cost $0.14: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.

How long does harlequin take to install?

2 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 harlequin need a GPU?

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

What goes wrong when installing harlequin?

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.

Where is the evidence for harlequin?

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.

harlequin

The SQL IDE for Your Terminal.

Runssource: GitHub homepagePythonMITcommit 5c463bf8b29e

Python, MIT licensed. The project labels itself: agent, cli, client, database, db, db cli, db client and duckdb.

harlequin runs. An Argusic agent installed it in 2 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Harlequin v2.15.0 installed via uv from source: all 1153 unit tests pass, ruff and mypy clean, hsql CLI executes SQL against DuckDB and SQLite adapters in table/csv/json formats, TUI launches on Xvfb display, and import-linter confirms all 5 contract boundaries are upheld.
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 60 of 100 (the mean of this project's run scores).

At a glance

verdict: Runs
Argusic Score: 60 / 100
cost of the verifying run: $0.14 (measured)
recorded runs: 2
last tested: 2026-09-29
stars: 6,431
forks: 178
open issues: 30
watchers: 23
size: 25 MB
created: 2023-05-02
last push: 2026-09-28

Subject data from GitHub, linked at the top of this page, refreshed 2026-09-29. 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 harlequin, 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.

Locale en_US.UTF-8 not available in minimal container (only C/C.utf8/POSIX installed). Tests errored at setup with HarlequinLocaleError.3 minutes

Install time: 2 minutes
Cold machine to finish: 41 minutes
Errors hit and fixed: 1 hit, 1 fixed with no human help
How the result was proved: uv run hsql -c 'select 1 as foo' returned 'foo | 1' (DuckDB); uv run hsql -a sqlite -c 'select 42' --format json returned '[{"answer":42}]'; uv run hsql -c 'select 1' -o /tmp/out.csv --format csv wrote correct CSV; uv run ruff check . returned 'All checks passed'; uv run mypy returned 'Success: no issues found in 160 source files'; uv run pytest -m 'not online' -n0 --tb=short tests/unit_tests/ all passed (1153 tests)
Model tokens used: 159,492
Exact commit tested: 5c463bf8b29e
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.

    ],
    \"test_depth\": \"tier1_real\",
    \"verified_how\": \"uv run hsql -c 'select 1 as foo' returned 'foo | 1' (DuckDB); uv run hsql -…
    \"final_state\": \"Harlequin v2.15.0 installed via uv from source: all 1153 unit tests pass, ru…
}
print(f\"ARGUSIC_RESULT:{json.dumps(result)}\")
PYEOF" in /work/repo
 succeeded in 0ms:
All done. Results delivered in the `ARGUSIC_RESULT:` line above. The only issue was the missing `en…
tokens used
159,492
All done. Results delivered in the `ARGUSIC_RESULT:` line above. The only issue was the missing `en…

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 2 minutes, faster than the median of the 53 comparable projects Argusic has measured.
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.

Of the 54 agent projects Argusic has installed and timed, harlequin was the 14th fastest to reach a running state, and 38 of 54 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 2 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

tested by	attempt	outcome	score	cost USD	when
Argusic Runner	2/3	Runs	100.00	0.14	2026-09-29 00:17 UTC
Argusic Runner	1/3	Did not run	20.00	0.14	2026-09-28 23:35 UTC

Topics (from GitHub)

agent cli client database db db-cli db-client duckdb mariadb mssql mysql odbc postgres python redshift snowflake sql sqlite textual tui

Embed the badge

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

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

Questions

Does harlequin run?: Yes. harlequin runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 1 error on the way, and recorded the session.
How did Argusic test harlequin?: On a fresh, disposable machine, with every command recorded and the repository pinned at commit 5c463bf8b29e. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test harlequin?: The run that produced this verdict cost $0.14: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does harlequin take to install?: 2 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 harlequin need a GPU?: Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing harlequin?: 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 harlequin compare with the alternatives?: Of the 54 agent projects Argusic has installed and timed, harlequin was the 14th fastest to reach a running state, and 38 of 54 reached one at all.
Where is the evidence for harlequin?: 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.