probe

AI-friendly semantic code search engine for large codebases. Combines ripgrep speed with tree-sitter AST parsing. Powers AI coding assistants with precise, context-aware code understanding.

Runssource: GitHubhomepageRustApache-2.0commit 1ee1ecb7f459

Rust, Apache-2.0 licensed. The project labels itself: ai, ai coder, ast, cli, code search, mcp, nodejs sdk and ripgrep.

probe runs. An Argusic agent installed it in 25 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Probe v0.6.0 builds from source with 469/469 core tests passing; the CLI binary searches, extracts, and outputs JSON correctly for Rust, Go, JavaScript, and other supported languages.

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
$0.16 (measured)
recorded runs
1
last tested
stars
741
forks
64
open issues
27
watchers
7
size
23 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 probe, 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.

  • Missing tests/schemas/json_output_schema.json — 4 schema validation tests failed to load the file2 minutes
Install time
25 minutes
Cold machine to finish
35 minutes
Errors hit and fixed
1 hit, 1 fixed with no human help
How the result was proved
probe --version returned 'probe-code 0.6.0'; probe search 'fn main' --format json returned 2 results with valid JSON and count=2; cargo test --lib passed 428/428, integration_tests passed 11/11, cli_tests passed 21/21, property_tests passed 5/5, json_schema_validation_tests passed 4/4
Model tokens used
142,091
Exact commit tested
1ee1ecb7f459
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.

**Error encountered and fixed:** The file `tests/schemas/json_output_schema.json` was missing from …
tokens used
142,091
All done. Let me compile the final report.
**Test results summary:**
- `cargo test --lib`: **428 passed**, 0 failed, 1 ignored
- `cargo test --test integration_tests`: **11 passed**, 0 failed
- `cargo test --test cli_tests`: **21 passed**, 0 failed, 1 ignored
- `cargo test --test property_tests`: **5 passed**, 0 failed
- `cargo test --test json_schema_validation_tests`: **4 passed**, 0 failed — after creating the mis…
- `cargo test --test lsp_comprehensive_tests`: 2 passed, 11 failed (requires `gopls` and `typescrip…
**Error encountered and fixed:** The file `tests/schemas/json_output_schema.json` was missing from …

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 25 minutes to install, slower than the median of the 236 comparable projects Argusic has measured.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 237 ai projects Argusic has installed and timed, probe was the 214th 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.

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 Runner1/3Runs100.000.16

Topics (from GitHub)

aiai-coderastclicode-searchmcpnodejs-sdkripgreprustsearch-enginesemantic-searchtree-sitter

Embed the badge

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

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

Questions

Does probe run?
Yes. probe runs. Argusic installed and launched it on a clean machine in 25 minutes, hitting 1 error on the way, and recorded the session.
How did Argusic test probe?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 1ee1ecb7f459. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test probe?
The run that produced this verdict cost $0.16: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does probe take to install?
25 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 probe need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing probe?
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 probe compare with the alternatives?
Of the 237 ai projects Argusic has installed and timed, probe was the 214th fastest to reach a running state, and 168 of 237 reached one at all.
Where is the evidence for probe?
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