wmux

The ADE for AI agents. Automate everything else. Do your true work.

Runssource: GitHubhomepageTypeScriptMITcommit 40d4b1f56896

TypeScript, MIT licensed. The project labels itself: ade, agent development environment, agentic ai, ai agents, automation, browser automation, claude code and codex.

wmux runs. An Argusic agent installed it in 15 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

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
$0.09 (measured)
recorded runs
1
last tested
stars
459
forks
78
open issues
28
watchers
3
size
162 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 wmux, 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.

  • npm install required node >=22, npm >=11 but container had node 18 / npm 9.23 minutes
  • test:runtime — 1 test failed: 'paints completed synchronized frames while OpenCode-style output remains active' — Playwright browser not installed2 minutes
  • test:parallel — 1 test failed: 'pane-owned Codex Unix relay > supports the native daemon short-path socket link without losing ownership checks' — Unsafe Codex socket directory because /tmp is 1777
Install time
15 minutes
Cold machine to finish
23 minutes
Errors hit and fixed
3 hit, 3 fixed with no human help
How the result was proved
npm run test:parallel, 1256/1259 test files passed, 19078/19108 tests passed, 1 env-specific failure (Codex socket dir mode); npm run test:runtime, 20/29 files passed, 250/334 tests passed, 0 failures after Playwright chromium install; npm run test:harness, 4/4 passed, 59/62 tests passed; daemon started, status returned ok with PID/uptime/bootTrace; daemon stopped cleanly; CLI --help printed 50+ commands
Model tokens used
249,002
Exact commit tested
40d4b1f56896
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.

  uptime: 2
  sessions: 0
  eventLoopLagMs: 20
  bootTrace: {"jsStartEpochMs":1792598672604,"marks":{"main-start":1792598672606,"lock-acquired":17…
  spawnedByVersion: "3.62.1"
  channelsEpoch: 1
  eventLogFormatVersion: 1
wmux daemon stopped.
Now let me compile the final report:
tokens used
249,002
Now let me compile the final report:

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.

What did not, or is not known

  • Took 15 minutes to install, slower than the median of the 38 comparable projects Argusic has measured.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 39 agentic-ai projects Argusic has installed and timed, wmux was the 34th fastest to reach a running state, and 31 of 39 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 Runner1/3Runs100.000.09

Topics (from GitHub)

adeagent-development-environmentagentic-aiai-agentsautomationbrowser-automationclaude-codecodexcoding-agentdeveloper-toolsgemini-cligit-worktreemacosmcp-servermulti-agentterminal-multiplexertmuxwindowsworkspace-multiplexer

Embed the badge

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

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

Questions

Does wmux run?
Yes. wmux runs. Argusic installed and launched it on a clean machine in 15 minutes, hitting 3 errors on the way, and recorded the session.
How did Argusic test wmux?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 40d4b1f56896. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test wmux?
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 wmux take to install?
15 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 wmux need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing wmux?
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 wmux compare with the alternatives?
Of the 39 agentic-ai projects Argusic has installed and timed, wmux was the 34th fastest to reach a running state, and 31 of 39 reached one at all.
Where is the evidence for wmux?
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