next-plaid

NextPlaid, ColGREP: Multi-vector search, from database to coding agents.

Runssource: GitHubhomepageRustApache-2.0commit 00e26aae0006

Rust, Apache-2.0 licensed. The project labels itself: agentic rag, cli, grep, multi vector and vector database.

next-plaid runs. An Argusic agent installed it in 15 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

The Rust workspace compiles, all 1062 unit tests pass, both binaries respond to help/version, NextPlaid API serves CRUD endpoints (index create/add documents/search returning real scores), and ColGREP builds indexes and performs semantic code search with ONNX model inference.

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
$0.04 (measured)
recorded runs
1
last tested
stars
624
forks
68
open issues
31
watchers
2
size
27 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 next-plaid, 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.

  • Rust toolchain not found in container1 minute
Install time
15 minutes
Cold machine to finish
14 minutes
Errors hit and fixed
1 hit, 1 fixed with no human help
How the result was proved
cargo test --workspace: all 1062 tests passed. API: curl POST/GET/update/search returned HTTP 200/202/200 with correct data. colgrep --version returned 1.7.0. colgrep init indexed 97 units, colgrep 'tree sitter parsing' --json returned ranked results.
Model tokens used
208,290
Exact commit tested
00e26aae0006
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

Watch the session

The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.

A recording of attempt 1, run , the attempt that decided the verdict above. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

tokens used
208,290
Here's a summary of everything I did and found:
**Installation:** The Rust toolchain wasn't available in the container. Installed `rustup`, set the…
**Build:** `cargo check` and `cargo build --release` both succeeded with no errors or warnings.
**Tests:** All 1062 unit tests across all four workspace crates passed with 0 failures.
**App verification:**
- `colgrep --version` → `colgrep 1.7.0`
- `next-plaid-api --help` → printed full usage
- NextPlaid API server launched on port 8080, responded to `GET /indices` (200, `[]`), `POST /indic…
- `colgrep init` on the colgrep source code indexed 97 code units in ~30s using the LateOn-Code-edg…
- `colgrep "tree sitter parsing" --json` returned ranked semantic search results

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 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 Apache-2.0, as reported by its host.

What did not, or is not known

  • Took 15 minutes to install, slower than the median of the 3 comparable projects Argusic has measured.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 4 agentic-rag projects Argusic has installed and timed, next-plaid was the 3rd fastest to reach a running state, and 2 of 4 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 byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs100.000.04

Topics (from GitHub)

agentic-ragcligrepmulti-vectorvector-database

Embed the badge

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

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

Questions

Does next-plaid run?
Yes. next-plaid runs. Argusic installed and launched it on a clean machine in 15 minutes, hitting 1 error on the way, and recorded the session.
How did Argusic test next-plaid?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 00e26aae0006. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test next-plaid?
The run that produced this verdict cost $0.04: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does next-plaid 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 next-plaid need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing next-plaid?
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 next-plaid compare with the alternatives?
Of the 4 agentic-rag projects Argusic has installed and timed, next-plaid was the 3rd fastest to reach a running state, and 2 of 4 reached one at all.
Where is the evidence for next-plaid?
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.

Discussion