Yes. mex runs. Argusic installed and launched it on a clean machine in 13 minutes, hitting 3 errors on the way, and recorded the session.

How did Argusic test mex?

On a fresh, disposable machine, with every command recorded and the repository pinned at commit 490ffe5017c6. 2 attempts are recorded, and the full method is on the methodology page.

What did it cost to test mex?

The run that produced this verdict cost $0.13: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.

How long does mex take to install?

13 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.

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

What goes wrong when installing mex?

3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.

Where is the evidence for mex?

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.

mex

Team memory for engineers and their AI agents. Lives in your repo. Shared through Git.

Runssource: GitHub homepageTypeScriptMITcommit 490ffe5017c6

TypeScript, MIT licensed. The project labels itself: agent skill, agent skills, claude code, claude code skills, cli tool, code graph, codex and context management.

mex runs. An Argusic agent installed it in 13 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

MEX 0.8.2 built, typechecked, and tested with Node 24.0.0 (downloaded). CLI version 0.8.2 confirmed. Test suite passes 4288/4317 tests with 6 pre-existing failures (4 timeouts on constrained hardware, 2 test bugs treating directories as files). npm install, build, and typecheck all succeed. FTS5 full-text search verified functional.
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 60 of 100 (the mean of this project's run scores).

At a glance

verdict: Runs
Argusic Score: 60 / 100
cost of the verifying run: $0.13 (measured)
recorded runs: 2
last tested: 2026-10-06
stars: 1,753
forks: 139
open issues: 30
watchers: 4
size: 21 MB
created: 2026-03-21
last push: 2026-10-05

Subject data from GitHub, linked at the top of this page, refreshed 2026-10-06. 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 mex, 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 22.5.0 official build lacks SQLite FTS5 support2 minutes
Node.js v18.19.1 pre-installed but project requires >=22.51 minute
node:sqlite module needs --experimental-sqlite flag in Node 22

Install time: 13 minutes
Cold machine to finish: 26 minutes
Errors hit and fixed: 3 hit, 3 fixed with no human help
How the result was proved: npm test: 4288 passed / 4317 total, 271/277 files passed. node dist/cli.js --version returned 0.8.2. FTS5 verified with CREATE VIRTUAL TABLE USING fts5 + INSERT + MATCH query.
Model tokens used: 158,196
Exact commit tested: 490ffe5017c6
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.

db.close();
\" && echo \"FTS5 functional verification: PASSED\"" in /work/repo
 succeeded in 0ms:
FTS5 search result: {"x":"hello world"}
(node:48675) ExperimentalWarning: SQLite is an experimental feature and might change at any time
(Use `node --trace-warnings ...` to show where the warning was created)
FTS5 functional verification: PASSED
exec
/bin/sh -lc "echo \"ARGUSIC_RESULT:{\\\"install_succeeded\\\":true,\\\"launch_succeeded\\\":true,\\…
 succeeded in 0ms:
tokens used
158,196

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 3 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 MIT, as reported by its host.
Measured 2 times, so the result is not a one-off.

What did not, or is not known

Took 13 minutes to install, slower than the median of the 4 comparable projects Argusic has measured.

Of the 5 agent-skill projects Argusic has installed and timed, mex was the 5th fastest to reach a running state, and 3 of 5 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	2/3	Runs	100.00	0.13	2026-10-06 02:47 UTC
Argusic Runner	1/3	Did not run	20.00	0.50	2026-10-06 02:08 UTC

Topics (from GitHub)

agent-skill agent-skills claude-code claude-code-skills cli-tool code-graph codex context-management cursor developer-tools documentation git knowledge-graph llm mcp-server memory-management project-memory tree-sitter typescript

Embed the badge

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

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

Questions

Does mex run?: Yes. mex runs. Argusic installed and launched it on a clean machine in 13 minutes, hitting 3 errors on the way, and recorded the session.
How did Argusic test mex?: On a fresh, disposable machine, with every command recorded and the repository pinned at commit 490ffe5017c6. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test mex?: The run that produced this verdict cost $0.13: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does mex take to install?: 13 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 mex need a GPU?: Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing mex?: 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does mex compare with the alternatives?: Of the 5 agent-skill projects Argusic has installed and timed, mex was the 5th fastest to reach a running state, and 3 of 5 reached one at all.
Where is the evidence for mex?: 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.

mex