SeaGOAT

local-first semantic code search engine

Runssource: GitHubhomepagePythonMITcommit dda7778020f4

Python, MIT licensed. The project labels itself: ai, ai project, code search, code search engine, embeddings, grep, grep like and llm.

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

SeaGOAT v1.2.0 installs via poetry, starts a local server, responds to status queries, and returns correct semantic search results for a test repository. 190 of 204 tests pass; 12 snapshot tests fail due to ONNX model processing timeout on this CPU.

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
$0.09 (measured)
recorded runs
2
last tested
stars
1,320
forks
97
open issues
38
watchers
6
size
25 MB
created
last push

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.

Time lost to each failure while testing SeaGOAT, 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.

  • 12 snapshot tests error: ONNX MiniLM embedding model inference times out (>120s) on CPU during test fixture setup5 minutes
Install time
1 minutes
Cold machine to finish
30 minutes
Errors hit and fixed
1 hit, 1 fixed with no human help
How the result was proved
poetry install succeeded; seagoat-server start on /tmp/test-repo (port 19999) responded at /status with 'accuracy.percentage: 100'; gt 'hello world' /tmp/test-repo returned correct lines 'def hello():' and 'return 'world'' on stdout; 190/190 core tests passed (--timeout=60)
Model tokens used
108,649
Exact commit tested
dda7778020f4
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_result_sorting: 5/5 passed
  - test_ripgrep: 8/8 passed
  - test_server: 21/21 passed
  - test_snapshot: 0/12 passed (ONNX timeout)
  - test_source_ripgrep: not found in earlier runs (assumed 0 collected)
Total core: 190/190 passed, snapshot: 0/12 errors, grand: 190/204
Now I have all the data. Let me compile the final report.
2026-10-08T23:13:31.385771Z ERROR codex_core::session: failed to record rollout items: thread 01a11…
2026-10-08T23:13:31.385952Z ERROR codex_core::session: failed to record rollout items: thread 01a11…
tokens used
108,649
Now I have all the data. Let me compile the final report.

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 1 minute, faster than the median of the 236 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 237 ai projects Argusic has installed and timed, SeaGOAT was the 37th fastest to reach a running state, and 168 of 237 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 1 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 byattemptoutcomescorecost USDwhen
Argusic Runner2/3Did not run20.000.79
Argusic Runner1/3Runs100.000.09

Topics (from GitHub)

aiai-projectcode-searchcode-search-engineembeddingsgrepgrep-likellmregular-expressionripgrepvector-databasevector-embeddings

Embed the badge

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

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

Questions

Does SeaGOAT run?
Yes. SeaGOAT runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 1 error on the way, and recorded the session.
How did Argusic test SeaGOAT?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit dda7778020f4. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test SeaGOAT?
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 SeaGOAT take to install?
1 minute in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
Does SeaGOAT need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing SeaGOAT?
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 SeaGOAT compare with the alternatives?
Of the 237 ai projects Argusic has installed and timed, SeaGOAT was the 37th fastest to reach a running state, and 168 of 237 reached one at all.
Where is the evidence for SeaGOAT?
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.

Discussion