Yes. leon runs. Argusic installed and launched it on a clean machine in 8 minutes, hitting 4 errors on the way, and recorded the session.

How did Argusic test leon?

On a fresh, disposable machine, with every command recorded and the repository pinned at commit a8f2052fb6d9. 2 attempts are recorded, and the full method is on the methodology page.

What did it cost to test leon?

The run that produced this verdict cost $0.12: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.

How long does leon take to install?

8 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 leon need a GPU?

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

What goes wrong when installing leon?

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.

Where is the evidence for leon?

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.

leon

🧠 Leon is your open-source personal assistant.

Runssource: GitHub homepageTypeScriptMITcommit a8f2052fb6d9

TypeScript, MIT licensed. The project labels itself: ai, ai agent, ai assistant, artificial intelligence, assistant, automation, bot and chatbot.

leon runs. An Argusic agent installed it in 8 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Leon server installs, builds, serves HTTP on port 5366, and passes all 371 unit tests with Node.js v24 in CI mode (no local AI or voice models).
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: $0.12 (measured)
recorded runs: 2
last tested: 2026-11-03
stars: 17,652
forks: 1,479
open issues: 119
watchers: 267
size: 141 MB
created: 2019-02-10
last push: 2026-11-08

Subject data from GitHub, linked at the top of this page, refreshed 2026-11-09. 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 leon, 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.

System Node.js v18 does not meet >=24 requirement3 minutes
llama.cpp build OOM-killed during cmake2 minutes
node-llama-cpp postinstall crashes on Node 18 JSON-with syntax1 minute
Ninja setup requires unzip command (not in container)1 minute

Install time: 8 minutes
Cold machine to finish: 10 minutes
Errors hit and fixed: 4 hit, 4 fixed with no human help
How the result was proved: pnpm run test:unit exited 0, 40 test files, 371 tests passed; server GET / returned HTTP 200
Model tokens used: 78,472
Exact commit tested: a8f2052fb6d9
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.

- llama.cpp build OOM-killed (skipped via CI mode; not needed for server-only testing)
tokens used
78,472
Here's the complete report on this install & verification run:
**Install:** The project requires Node.js >=24 (system has v18). I downloaded Node.js v24.21.0 dire…
**Verification:** All 371 unit tests pass (40 test files). The server starts and responds 200 on `G…
**Errors:**
- Node.js v18 system binary insufficient (fixed by using standalone v24 binary)
- `pnpm install` engine-strict blocked v18 (fixed by using v24 and `--ignore-scripts`)
- `node-llama-cpp` postinstall crashed on Node.js 18 JSON-with syntax (worked around with `--ignore…
- Ninja setup requires `unzip` (skipped via CI mode; not needed for server-only testing)
- llama.cpp build OOM-killed (skipped via CI mode; not needed for server-only testing)

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 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 8 minutes to install, slower than the median of the 232 comparable projects Argusic has measured.

Of the 233 ai projects Argusic has installed and timed, leon was the 143rd fastest to reach a running state, and 156 of 233 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 8 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 by	attempt	outcome	score	cost USD	when
Argusic Runner	2/3	Runs	100.00	0.12	2026-11-03 01:25 UTC
Argusic Runner	1/3	Runs	100.00	0.04	2026-09-26 04:22 UTC

Embed the badge

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

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

Questions

Does leon run?: Yes. leon runs. Argusic installed and launched it on a clean machine in 8 minutes, hitting 4 errors on the way, and recorded the session.
How did Argusic test leon?: On a fresh, disposable machine, with every command recorded and the repository pinned at commit a8f2052fb6d9. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test leon?: The run that produced this verdict cost $0.12: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does leon take to install?: 8 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 leon need a GPU?: Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing leon?: 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 leon compare with the alternatives?: Of the 233 ai projects Argusic has installed and timed, leon was the 143rd fastest to reach a running state, and 156 of 233 reached one at all.
Where is the evidence for leon?: 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.