Menu

What broke while up to 30 AI agents built my coding agent, and the rule each failure produced
📰

What broke while up to 30 AI agents built my coding agent, and the rule each failure produced

DEV Community: opensource·Randy Northrup·12 days ago
#e4fF6uJS
#devtoopensource#devto#dev#lane#code
Long article (1035 words) — no AI summary yet.
Reading 0:00
15s threshold

Muse Spark Code, my open source coding agent for Meta's Muse Spark, is mostly built by other agents. Claude orchestrates. Codex and Muse agents build in small lanes, and a different agent reviews every lane before it merges. At its peak, one orchestrator ran up to 30 coding and review agents across three rigs: a Kubuntu box, a Mac mini and a Windows 11 VM. Since the repo went up on September 22 it has merged 229 pull requests and shipped 41 releases.

It also broke, a lot. Every failure that generalises goes into a register in the repo, with what happened, the rule that prevents it, and the milestone in the app that has to enforce that rule. It has 129 numbered entries now. These are the ones that taught me the most.

Silence is never success

A status poll failed, and the orchestrator read the failure as "still running". Finished Windows lanes went unreported for 40 minutes. Rule: a job is running, finished, or unknown since {time} . A failed poll makes it unknown, never running.…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.