lcu

Codex computer use, decoupled from the app, for usage inside any harness.

Runs with mockssource: GitHubhomepageJavaScriptMITcommit 748303e9315e

JavaScript, MIT licensed. The project labels itself: accessibility, agent skills, browser automation, claude code, codex cli, computer use, desktop automation and library.

lcu runs, with stand-ins for the services it depends on. An Argusic agent installed it in 7.5 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

LCU 0.9.1 builds into a thin release archive, installs into a prefix, passes all 435 Python unit tests, and answers version via the installed binary; 7 of 103 Node.js adapter tests fail on Node 18 due to MockTimers API version mismatch and missing .ts loader, both resolved by Node 20+.

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 92 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs with mocks
Argusic Score
92 / 100
cost of the verifying run
$0.09 (measured)
recorded runs
2
last tested
stars
2,456
forks
172
open issues
1
watchers
6
size
13 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.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • MockTimers.enable in Node 18 expects 'timers' as an Array, used in adapters/test/client.test.mjs (4 tests fail)
  • Node 18 cannot load .ts ESM files, causing adapters/test/omp.test.mjs, pi-approval.test.mjs, pi.test.mjs to fail
  • MCP server exits on mock app because stub node binary exits immediately
Install time
8 minutes
Cold machine to finish
11 minutes
Errors hit and fixed
3 hit, 3 fixed with no human help
How the result was proved
python3 -m unittest discover -b -s tests -p 'test_*.py' exited 0, 435 passed, 2 skipped; lcu --version returned 'lcu 0.9.1 (ChatGPT linux 26.924.22138; CUA 6.0.0)'; build_bundle.py produced the release archive
Model tokens used
225,875
Exact commit tested
748303e9315e
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
Behaviour against real services
this run was verified against stand-in services only

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

**Install**: Succeeded with a mock ChatGPT app fixture. LCU 0.9.1 recognized the app (ChatGPT linux…
**Python unit tests**: All 435 tests pass (2 skipped: macOS-only).
**Node adapter tests**: 88 pass, 7 fail, 8 skip. All 7 failures are Node.js v18 compatibility issue…
**The MCP server** (`lcu` with no arguments) exits immediately because the mock app's `node` binary…
tokens used
225,875
Now I have a complete picture. Here's my report:
**Build**: Succeeded on first try. `scripts/build_bundle.py` produced `dist/lcu-0.9.1-linux-x64.tar…
**Install**: Succeeded with a mock ChatGPT app fixture. LCU 0.9.1 recognized the app (ChatGPT linux…
**Python unit tests**: All 435 tests pass (2 skipped: macOS-only).
**Node adapter tests**: 88 pass, 7 fail, 8 skip. All 7 failures are Node.js v18 compatibility issue…
**The MCP server** (`lcu` with no arguments) exits immediately because the mock app's `node` binary…

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

  • Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
  • 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

  • Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
  • Took 7.5 minutes to install, slower than the median of the 11 comparable projects Argusic has measured.

Of the 12 accessibility projects Argusic has installed and timed, lcu was the 7th fastest to reach a running state, and 11 of 12 reached one at all.

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 Runner2/3Runs with mocks92.000.09
Argusic Runner1/3Runs with mocks92.000.09

Topics (from GitHub)

accessibilityagent-skillsbrowser-automationclaude-codecodex-clicomputer-usedesktop-automationlibrarylinuxmacosmcppi-agentx11

Embed the badge

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

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

Questions

Does lcu run?
lcu runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 8 minutes, hitting 3 errors on the way, and recorded the session.
How did Argusic test lcu?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 748303e9315e. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test lcu?
The run that produced this verdict cost $0.09: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does lcu take to install?
7.5 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 lcu need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing lcu?
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 lcu compare with the alternatives?
Of the 12 accessibility projects Argusic has installed and timed, lcu was the 7th fastest to reach a running state, and 11 of 12 reached one at all.
Where is the evidence for lcu?
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