Yes. zvec runs. Argusic installed and launched it on a clean machine in 50 minutes, hitting 5 errors on the way, and recorded the session.

How did Argusic test zvec?

On a fresh, disposable machine, with every command recorded and the repository pinned at commit 53c1bb60a0e5. One attempt is recorded, and the full method is on the methodology page.

What did it cost to test zvec?

The run that produced this verdict cost $0.29: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.

How long does zvec take to install?

49.6 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 zvec need a GPU?

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

What goes wrong when installing zvec?

5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.

Where is the evidence for zvec?

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.

zvec

A lightweight, lightning-fast, in-process vector database

Runssource: GitHub homepageC++Apache-2.0commit 53c1bb60a0e5

C++, Apache-2.0 licensed. The project labels itself: agent skills, db, embedded, faiss, fts, fulltext search, hnsw and llm memory.

zvec runs. An Argusic agent installed it in 49.6 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Zvec v0.7.0 prebuilt wheel and from-source build both work: the Python SDK successfully creates vectors collections, inserts documents, and returns ranked similarity search results, and the 1543-test suite passes with zero failures.
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: $0.29 (measured)
recorded runs: 1
last tested: 2026-09-26
stars: 16,007
forks: 1,004
open issues: 64
watchers: 76
size: 8 MB
created: 2025-12-05
last push: 2026-09-24

Subject data from GitHub, linked at the top of this page, refreshed 2026-09-26. 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 zvec, 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.

Parallel build of _zvec.so fails because static lib targets (core_knn_flat_static, etc.) are not built before linking7.3 minutes
pybind11::module INTERFACE_INCLUDE_DIRECTORIES hard-codes /usr/include/python3.12 from sysconfig; system cmake 3.28 vs pip cmake 3.31 behaves differently5.8 minutes
Python.h includes <x86_64-linux-gnu/python3.12/pyconfig.h> which was not present2.7 minutes
python3.12-dev headers not installed - CMake/pybind11 FindPythonLibsNew resolves INCLUDEPY to /usr/include/python3.12 which doesn't exist2.5 minutes
Pip-installed Python wrapper layer v0.7.0 mismatched freshly-built _zvec.so API (tuple vs _Doc objects)0.5 minutes

Install time: 50 minutes
Cold machine to finish: 58 minutes
Errors hit and fixed: 5 hit, 5 fixed with no human help
How the result was proved: python -m pytest python/tests/ --tb=line -n=0 returned 1543 passed, 15 skipped, 0 failed; python -c example from README returned correct sorted results
Model tokens used: 1,440,696
Exact commit tested: 53c1bb60a0e5
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.

  "score": 0.30000001192092896,
  "fields": {},
  "vectors": {}
}, {
  "id": "doc_1",
  "score": 0.23000001907348633,
  "fields": {},
  "vectors": {}
}]
ZVEC WORKS
tokens used
1,440,696

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 5 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 Apache-2.0, as reported by its host.

What did not, or is not known

Took 49.6 minutes to install, slower than the median of the 14 comparable projects Argusic has measured.
Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 15 agent-skills projects Argusic has installed and timed, zvec was the 15th fastest to reach a running state, and 12 of 15 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	0.29	2026-09-26 11:13 UTC

Topics (from GitHub)

agent-skills db embedded faiss fts fulltext-search hnsw llm-memory local rag search-engine semantic-search similarity-search vector-database vector-db

Embed the badge

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

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

Questions

Does zvec run?: Yes. zvec runs. Argusic installed and launched it on a clean machine in 50 minutes, hitting 5 errors on the way, and recorded the session.
How did Argusic test zvec?: On a fresh, disposable machine, with every command recorded and the repository pinned at commit 53c1bb60a0e5. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test zvec?: The run that produced this verdict cost $0.29: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does zvec take to install?: 49.6 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 zvec need a GPU?: Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing zvec?: 5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does zvec compare with the alternatives?: Of the 15 agent-skills projects Argusic has installed and timed, zvec was the 15th fastest to reach a running state, and 12 of 15 reached one at all.
Where is the evidence for zvec?: 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.