xerj

AI search engine and MCP server for bots and agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search, code search without grep, agent memory and RAG. Elasticsearch-compatible API; Corpus Hub serves hundreds of reference memory corpora.

Runssource: GitHubhomepageRustApache-2.0commit fa27e936272c

Rust, Apache-2.0 licensed. The project labels itself: agent memory, ai agents, bm25, claude code, cli, code search, cursor and database.

xerj runs. An Argusic agent installed it in 33 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

XERJ v1.0.0-rc.77 built from source in 2m06s (quick profile), serving ES-compat API on :9200 with autoindex and MCP server working; test suites pass except 2 IPv6 bind failures specific to this container

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
2
last tested
stars
19,210
forks
1,444
open issues
124
watchers
193
size
302 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 xerj, 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.

  • Server died after shell session ended (SIGHUP from pipe)4 minutes
  • No Rust toolchain installed3 minutes
  • autoindex on full engine folder failed: tcp connect error (os error 99)3 minutes
  • 2 of 71 xerj-server tests failed: IPv6 loopback bind on ::1 (os error 99)
Install time
33 minutes
Cold machine to finish
36 minutes
Errors hit and fixed
4 hit, 4 fixed with no human help
How the result was proved
cargo test --profile quick -p xerj-server: 69/71 passed (2 IPv6 env failures); cargo test -p xerj-autoindex: 5/5 passed; cargo test -p xerj-mcp: 40/40 passed; curl localhost:9200 returned 200; autoindex docs/ completed: 18 datasets, 9681 records; search returned 458 hits
Model tokens used
65,608
Exact commit tested
fa27e936272c
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.

Tests started ~23:20 and later runs completed at various times
First test (xerj-server): 69 passed, 2 env-specific failures
xerj-autoindex tests: 5 passed
xerj-mcp tests: 40 passed
exec
/bin/sh -lc 'date +%s' in /work/repo
 succeeded in 0ms:
1793662933
Now let me compose the final result. The install time was approximately 33 minutes from start to fi…
tokens used
65,608
Now let me compose the final result. The install time was approximately 33 minutes from start to fi…

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 4 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.
  • Measured 2 times, so the result is not a one-off.

What did not, or is not known

  • Took 33 minutes to install, slower than the median of the 3 comparable projects Argusic has measured.

Of the 4 ai-search projects Argusic has installed and timed, xerj was the 4th fastest to reach a running state, and 3 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 Runner2/3Runs100.000.16
Argusic Runner1/3Runs100.000.02

Topics (from GitHub)

agent-memoryai-agentsbm25claude-codeclicode-searchcursordatabaseelasticsearchfull-text-searchhybrid-searchjsonllocal-firstmcpmcp-servermodel-context-protocolragrustsearch-enginevector-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/xerj.svg)](https://argusic.com/subject/xerj)

Questions

Does xerj run?
Yes. xerj runs. Argusic installed and launched it on a clean machine in 33 minutes, hitting 4 errors on the way, and recorded the session.
How did Argusic test xerj?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit fa27e936272c. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test xerj?
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 xerj take to install?
33 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 xerj need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing xerj?
4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does xerj compare with the alternatives?
Of the 4 ai-search projects Argusic has installed and timed, xerj was the 4th fastest to reach a running state, and 3 of 4 reached one at all.
Where is the evidence for xerj?
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