Yes. loopx runs. Argusic installed and launched it on a clean machine in 18 minutes, hitting 3 errors on the way, and recorded the session.

How did Argusic test loopx?

On a fresh, disposable machine, with every command recorded and the repository pinned at commit d42adb874d04. One attempt is recorded, and the full method is on the methodology page.

What did it cost to test loopx?

The run that produced this verdict cost $0.31: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.

How long does loopx take to install?

18 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 loopx need a GPU?

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

What goes wrong when installing loopx?

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 loopx?

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.

loopx

A control plane with a durable state kernel for long-horizon agents and teams. Keep work moving and improving across sessions, with less human attention.

Runssource: GitHub homepagePythonApache-2.0commit d42adb874d04

Python, Apache-2.0 licensed. The project labels itself: agent control plane, agent harness, ai agents, claude code, codex, dsh plugin, local first and long horizon agents.

loopx runs. An Argusic agent installed it in 18 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

LoopX 1.2.0 installed from source in venv with Node.js 22; CLI responds, doctor passes, demo workspace serves on localhost, 125/125 TypeScript control plane tests pass, canary and smoke suites pass, main Python test suite collects 12206 tests with 3 pre-existing failures (stale registry manifest, missing git worktree, pip wheel issue) unrelated to our changes
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: $0.31 (measured)
recorded runs: 1
last tested: 2026-09-29
stars: 6,111
forks: 590
open issues: 120
watchers: 29
size: 102 MB
created: 2026-05-31
last push: 2026-09-30

Subject data from GitHub, linked at the top of this page, refreshed 2026-09-30. 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 loopx, 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.

tests/control_plane/test_reviewed_promotion_cli.py failed to collect: ImportError for _workspace, _cli, _command, _env, REPO_ROOT from refactored module5 minutes
Python externally-managed-environment prevented system-wide pip install2 minutes
Node.js 18.19.1 was installed but project requires Node.js >=22.22.3 for the TypeScript control plane runtime1 minute

Install time: 18 minutes
Cold machine to finish: 59 minutes
Errors hit and fixed: 3 hit, 3 fixed with no human help
How the result was proved: loopx --help prints usage header; loopx doctor exits 0; loopx status returns JSON; demo workspace prepare creates 3-goal state; demo workspace serve returns HTTP 302; canary smokes pass (25 pytest + 125 TS tests + 4 example smokes); comprehensive pytest runs across canary(25p), presentation(34p), capabilities(~600p across benchmark/change/periodic/issue-fix/machine), cli_commands(124p), and examples(4p) all pass
Model tokens used: 254,453
Exact commit tested: d42adb874d04
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.

 succeeded in 0ms:
Done. Final compilation starting.
Now I have all the data I need. Let me compile the final ARGUSIC_RESULT.
exec
/bin/sh -lc "cat << 'EOF'
EOF" in /work/repo
 succeeded in 0ms:
All verification is done. The environment is fully operational with LoopX 1.2.0 working end-to-end.
2026-09-29T05:15:13.378361Z ERROR codex_core::session: failed to record rollout items: thread 01a0e…
tokens used
254,453
All verification is done. The environment is fully operational with LoopX 1.2.0 working end-to-end.

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 18 minutes.
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 Apache-2.0, 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.

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	1/3	Runs	100.00	0.31	2026-09-29 05:15 UTC

Topics (from GitHub)

agent-control-plane agent-harness ai-agents claude-code codex dsh-plugin local-first long-horizon-agents loop-engineering multi-agent personal-agent rsi workflow-automation

Embed the badge

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

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

Questions

Does loopx run?: Yes. loopx runs. Argusic installed and launched it on a clean machine in 18 minutes, hitting 3 errors on the way, and recorded the session.
How did Argusic test loopx?: On a fresh, disposable machine, with every command recorded and the repository pinned at commit d42adb874d04. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test loopx?: The run that produced this verdict cost $0.31: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does loopx take to install?: 18 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 loopx need a GPU?: Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing loopx?: 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 loopx?: 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.