kelos

Kelos - The Kubernetes-native framework for orchestrating autonomous AI coding agents.

Runssource: GitHubGoApache-2.0commit 2ba9bb60f9fa

Go, Apache-2.0 licensed. The project labels itself: agentic ai, agentic coding, ai, ai agents, ci cd, claude, claude code and codex.

kelos runs. An Argusic agent installed it in 9.8 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.

All unit tests (45 packages) and integration tests (173 specs) pass, the CLI binary builds and answers commands, and the controller, webhook, and install CRDs work correctly against a real Kubernetes API server.

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
$0.03 (measured)
recorded runs
1
last tested
stars
360
forks
49
open issues
162
watchers
4
size
14 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.

Install time
10 minutes
Cold machine to finish
11 minutes
Errors hit and fixed
0 hit, 0 fixed with no human help
How the result was proved
make test exited 0 (45 packages all ok); make test-integration exited 0 (161/161 specs passed in 71.6s + 12/12 install specs passed in 254.3s); ./bin/kelos version printed 'latest'; ./bin/kelos help printed all 14 commands
Model tokens used
146,349
Exact commit tested
2ba9bb60f9fa
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

Watch the session

The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.

A recording of attempt 1, run , the attempt that decided the verdict above. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.

The end of the recording

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

/bin/sh -lc 'echo "Start: $(TZ=UTC date -d @$(date +%s -r /tmp/go.tar.gz) '"'+%H:%M:%S')\"; echo \"…
 succeeded in 0ms:
Start: 22:16:58
End: 22:26:44
All verification is complete. Here's the final report:
**Error count: 0** — no setup errors occurred. The Go toolchain was not pre-installed in the contai…
The project is a Go-based Kubernetes operator ("Kelos") for running coding agents as K8s workloads.…
tokens used
146,349
All verification is complete. Here's the final report:
**Error count: 0** — no setup errors occurred. The Go toolchain was not pre-installed in the contai…
The project is a Go-based Kubernetes operator ("Kelos") for running coding agents as K8s workloads.…

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.
  • Nothing broke on the way: zero errors between clone and running.
  • 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

  • Took 9.8 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, kelos was the 26th 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.
  • A quick evaluation: it was running 9.8 minutes after the clone.
  • Following its own README: the documented path worked with nothing to fix.

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 Runner1/3Runs100.000.03

Topics (from GitHub)

agentic-aiagentic-codingaiai-agentsci-cdclaudeclaude-codecodexcursorgeminikuberneteskubernetes-operatoropencode

Embed the badge

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

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

Questions

Does kelos run?
Yes. kelos runs. Argusic installed and launched it on a clean machine in 10 minutes, hitting 0 errors on the way, and recorded the session.
How did Argusic test kelos?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 2ba9bb60f9fa. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test kelos?
The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does kelos take to install?
9.8 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 kelos need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing kelos?
Nothing did, in the recorded run: zero errors between clone and running.
How does kelos compare with the alternatives?
Of the 39 agentic-ai projects Argusic has installed and timed, kelos was the 26th fastest to reach a running state, and 31 of 39 reached one at all.
Where is the evidence for kelos?
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