FRESH

Hacker News

Home

Show HN: Optio – Orchestrate AI coding agents in K8s to go from ticket to PR

87 points by jawiggins

by stingraycharles

4 subcomments

I’ve come to the realization that these kind of systems don’t work, and that a human in the loop is crucial for task planning; the LLM’s role being to identify issues, communicate the design / architecture, etc before it’s handed off, otherwise the LLM always ends up doing not entirely the correct thing.
How is this part tackled when all that you have is GH issues? Doesn’t this work only for the most trivial issues?

by denysvitali

0 subcomment

FWIW, a "cheaper" version of this is triggering Claude via GitHub Actions and `@claude`ing your agents like that. If you run your CI on Kubernets (ARC), it sounds pretty much the same

by naultic

1 subcomments

I'm working on something a little similar but mines more a dev tool vs process automation but I love where yours is headed. The biggest issue I've run into is handling retries with agents. My current solution is I have them set checkpoints so they can revert easily and when they can't make an edit or they can't get a test passing, they just restart from earlier state. Problem is this uses up lots of tokens on retries how did you handle this issue in your app?

by MrDarcy

1 subcomments

Looks cool, congrats on the launch. Is there any sandbox isolation from the k8s platform layer? Wondering if this is suitable for multiple tenants or customers.

by saltpath

2 subcomments

The parallel execution model makes sense for independent tickets but I'm wondering what happens when agent A is halfway through a PR touching shared/utils.py and agent B gets assigned a ticket that needs the same file. Does the orchestrator do any upfront dependency analysis to detect that, or do you just let them both run and deal with the conflict at merge time?

by verdverm

0 subcomment

I love k8s, but having it as a requirement for my agent setup is a non-starter. Kubernetes is one method for running, not the center piece.

by pianopatrick

5 subcomments

I wonder, based on your experience, how hard would it be to improve your system to have an AI agent review the software and suggest tickets?
Like, can an AI agent use a browser, attempt to use the software, find bugs and create a ticket? Can an AI agent use a browser, try to use the software and suggest new features?

by pistoriusp

0 subcomment

Hey @jawiggins, would you considering using https://github.com/redwoodjs/agent-ci?

by raised_hand

0 subcomment

Why K6? Is there a way I could run it without

by maxdo

1 subcomments

Is the pod per repo or per task ?

by fhouser

3 subcomments

Hot take: You should want to review your agents' output and progress.

by conception

1 subcomments

What’s the most complicated, finished project you’ve done with this?

by antihero

2 subcomments

And what stops it making total garbage that wrecks your codebase?

by abybaddi009

1 subcomments

Does this support skills and MCP?

by hmokiguess

1 subcomments

the misaligned columns in the claude made ASCII diagrams on the README really throw me off, why not fix them?
| | | |

by Andrew_McCarron

0 subcomment

[dead]

by MarcelinoGMX3C

0 subcomment

[dead]

by georaa

0 subcomment

[dead]

by ferreyadinarta

0 subcomment

[flagged]

by bmd1905

0 subcomment

[dead]

by rafaelbcs

0 subcomment

[dead]

by Acacian

0 subcomment

[dead]

by QubridAI

1 subcomments

[flagged]

by hustleracer

0 subcomment

[flagged]