Lexicon

The free open source offline writing assistant assist with grammar, rewriting & tone entirely on your machine.

Runssource: GitHubhomepageJavaScriptMITcommit 198a21c6428a

JavaScript, MIT licensed. The project labels itself: ai, desktop, grammar checker, javascript, local ai, local first, local llm and mac.

Lexicon runs. An Argusic agent installed it in 3.5 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Backend API responds on /health, all 11 backend tests pass, all 213 frontend tests pass, frontend builds and dev server starts.

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
$0.02 (measured)
recorded runs
1
last tested
stars
230
forks
20
open issues
6
watchers
1
size
17 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 Lexicon, 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 is too old for Vite 7 (requires 20+). Frontend build failed with crypto.hash is not a function.2.5 minutes
  • Java JRE not installed; LanguageTool proofreading engine cannot start
Install time
4 minutes
Cold machine to finish
3 minutes
Errors hit and fixed
2 hit, 2 fixed with no human help
How the result was proved
backend: python -m pytest backend/tests/ -v exited 0 (11/11 passed), uvicorn started and curl /health returned 200; frontend: npm run test exited 0 (213/213 passed), npm run build produced dist/, npm run dev started on :5173
Model tokens used
164,606
Exact commit tested
198a21c6428a
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.

Here's a clean summary of everything I verified:
**Backend**: Python venv created, deps installed, server starts and responds `{"status":"ok"}` on `…
**Frontend**: `npm ci` installed 516 packages. 213/213 tests pass with vitest. `npm run build` prod…
**Error encountered**: Vite 7.3.6 requires Node 20+ but only Node 18 was on `$PATH`. Fixed by insta…
**Missing dependency**: Java JRE is not available for LanguageTool proofreading. This is a runtime …
**Missing dependency**: `llama-cpp-python` is intentionally omitted from `requirements.txt` as an o…
exec
/bin/sh -lc "echo '{\"install_succeeded\": true, \"launch_succeeded\": true, \"install_minutes\": 3…
 succeeded in 0ms:
{"install_succeeded": true, "launch_succeeded": true, "install_minutes": 3.5, "errors": [{"msg": "N…
tokens used
164,606

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 3.5 minutes, faster than the median of the 236 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 MIT, 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 237 ai projects Argusic has installed and timed, Lexicon was the 110th 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.
  • A quick evaluation: it was running 3.5 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 byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs100.000.02

Topics (from GitHub)

aidesktopgrammar-checkerjavascriptlocal-ailocal-firstlocal-llmmacofflineoffline-firstollamaopen-sourceprivacyprivacy-focusedreviewself-hostedtext-editorwebappwindows

Embed the badge

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

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

Questions

Does Lexicon run?
Yes. Lexicon runs. Argusic installed and launched it on a clean machine in 4 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test Lexicon?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 198a21c6428a. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test Lexicon?
The run that produced this verdict cost $0.02: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does Lexicon take to install?
3.5 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 Lexicon need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing Lexicon?
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 Lexicon compare with the alternatives?
Of the 237 ai projects Argusic has installed and timed, Lexicon was the 110th fastest to reach a running state, and 168 of 237 reached one at all.
Where is the evidence for Lexicon?
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