Yes. zvec-grep runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 2 errors on the way, and recorded the session.

How did Argusic test zvec-grep?

On a fresh, disposable machine, with every command recorded and the repository pinned at commit 4c5b1a00402f. One attempt is recorded, and the full method is on the methodology page.

What did it cost to test zvec-grep?

The run that produced this verdict cost $0.23: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.

How long does zvec-grep take to install?

0.5 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-grep need a GPU?

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

What goes wrong when installing zvec-grep?

2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.

Where is the evidence for zvec-grep?

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-grep

Local-first search across your workspace, built for humans and AI agents.

Runssource: GitHubRustApache-2.0commit 4c5b1a00402f

Rust, Apache-2.0 licensed. The project labels itself: ai agents, bm25, cli, code search, full text search, local first, mcp and ripgrep.

zvec-grep runs. An Argusic agent installed it in 0.5 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

zvec-grep 0.2.1 TypeScript implementation builds, the CLI runs and searches, the test suite passes 698 of 700 tests (2 fail only due to disabled IPv6 loopback in the container) and all 9 e2e tests pass with real model inference using local/potion-code-16m-v2
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: $0.23 (measured)
recorded runs: 1
last tested: 2026-09-30
stars: 3,848
forks: 224
open issues: 66
watchers: 13
size: 41 MB
created: 2026-07-10
last push: 2026-09-30

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 zvec-grep, 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.

Node.js v18.19.1 installed but project requires >=220.5 minutes
2 shutdown origin tests fail for IPv6 ::1 loopback

Install time: under a minute
Cold machine to finish: 54 minutes
Errors hit and fixed: 2 hit, 2 fixed with no human help
How the result was proved: node --test ran 375 root tests (373 pass, 2 IPv6 environment skips), 39 integration tests (all pass), 9 e2e tests (all pass), 276 unit tests (all pass), 1 package test (pass); CLI --version returned '0.2.1'; CLI query against indexed workspace completed successfully
Model tokens used: 1,092,504
Exact commit tested: 4c5b1a00402f
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.

All tests and verification complete. Here's the final summary:
**What I did:**
1. **Node.js version gap**: Container had v18.19.1, project requires >=22. Downloaded Node.js v22.1…
2. **`npm ci`** — installed 388 packages successfully.
3. **`npm run build`** — TypeScript compilation succeeded.
4. **Test suites executed**:
   - Unit: **276 pass, 0 fail, 1 skip** (all good)
   - Root: **373 pass, 2 fail** — two IPv6-related shutdown origin tests (`::1`) fail because IPv6 …
   - Integration: **39 pass, 0 fail**
   - E2E: **9 pass, 0 fail**
   - Package: **1 pass, 0 fail**
5. **CLI verification**: `--version` prints `0.2.1`, `--help` shows full usage, `query` and `--stat…

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 0.5 minutes, faster than the median of the 32 comparable projects Argusic has measured.
Recovered from all 2 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

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

Of the 33 ai-agents projects Argusic has installed and timed, zvec-grep was the 3rd fastest to reach a running state, and 23 of 33 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 0.5 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	1/3	Runs	100.00	0.23	2026-09-30 20:09 UTC

Topics (from GitHub)

ai-agents bm25 cli code-search full-text-search local-first mcp ripgrep semantic-search vector-search

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-grep.svg)](https://argusic.com/subject/zvec-grep)

Questions

Does zvec-grep run?: Yes. zvec-grep runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test zvec-grep?: On a fresh, disposable machine, with every command recorded and the repository pinned at commit 4c5b1a00402f. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test zvec-grep?: The run that produced this verdict cost $0.23: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does zvec-grep take to install?: 0.5 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-grep need a GPU?: Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing zvec-grep?: 2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does zvec-grep compare with the alternatives?: Of the 33 ai-agents projects Argusic has installed and timed, zvec-grep was the 3rd fastest to reach a running state, and 23 of 33 reached one at all.
Where is the evidence for zvec-grep?: 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.