Show HN: Optio – Orchestrate AI coding agents in K8s to go from ticket to PR (github.com)

by jawiggins 59 comments 88 points
Read article View on HN

59 comments

[−] stingraycharles 51d ago
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?

[−] denysvitali 51d ago
FWIW, a "cheaper" version of this is triggering Claude via GitHub Actions and @claudeing your agents like that. If you run your CI on Kubernets (ARC), it sounds pretty much the same
[−] olegbk 45d ago
The feedback loop is what most people miss when they build these systems. You spin up the agent, it submits a PR, CI goes red, and suddenly you're back to being the bottleneck you were trying to eliminate.

One thing I ran into building something similar, agents are surprisingly good at fixing the exact error message they're given, but terrible at recognizing when they're going in circles. After the third retry on the same failing test, you're not getting a fix, you're getting increasingly creative excuses for why the test is wrong.

How deep does the self-healing go? Is there a retry limit before it escalates, or does it just keep going until you manually intervene?

[−] naultic 51d ago
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?
[−] MrDarcy 51d ago
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.
[−] saltpath 51d ago
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?
[−] verdverm 51d ago
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.
[−] pianopatrick 51d ago
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?

[−] pistoriusp 51d ago
Hey @jawiggins, would you considering using https://github.com/redwoodjs/agent-ci?
[−] raised_hand 51d ago
Why K6? Is there a way I could run it without
[−] maxdo 51d ago
Is the pod per repo or per task ?
[−] fhouser 51d ago
Hot take: You should want to review your agents' output and progress.
[−] conception 51d ago
What’s the most complicated, finished project you’ve done with this?
[−] antihero 51d ago
And what stops it making total garbage that wrecks your codebase?
[−] abybaddi009 51d ago
Does this support skills and MCP?
[−] hmokiguess 51d ago
the misaligned columns in the claude made ASCII diagrams on the README really throw me off, why not fix them?

| | | |

[−] psychomfa_tiger 43d ago
[flagged]
[−] MarcelinoGMX3C 51d ago
[dead]
[−] ferreyadinarta 51d ago
[flagged]
[−] rafaelbcs 51d ago
[dead]
[−] Andrew_McCarron 48d ago
[flagged]
[−] bmd1905 51d ago
[dead]
[−] Acacian 51d ago
[dead]
[−] georaa 48d ago
[flagged]
[−] QubridAI 51d ago
[flagged]
[−] hustleracer 51d ago
[flagged]