<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/i-run-a-fleet-of-ai-agents-across-three-machines-here-s-what-broke---kyle-jaejun-lee-krafton-lkf7juzk1" -->

---
title: I Run a Fleet of AI Agents Across Three Machines. Here's...
description: A developer at KRAFTON shares hard-won lessons from running a fleet of AI coding agents across three machines (a MacBook and two Linux boxes). Starting with a...
canonical: https://daily.dev/posts/i-run-a-fleet-of-ai-agents-across-three-machines-here-s-what-broke---kyle-jaejun-lee-krafton-lkf7juzk1
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: I Run a Fleet of AI Agents Across Three Machines. Here's What Broke. - Kyle Jaejun Lee, KRAFTON | daily.dev
og:description: A developer at KRAFTON shares hard-won lessons from running a fleet of AI coding agents across three machines (a MacBook and two Linux boxes). Starting with a...
og:url: https://daily.dev/posts/i-run-a-fleet-of-ai-agents-across-three-machines-here-s-what-broke---kyle-jaejun-lee-krafton-lkf7juzk1
og:image: https://api.daily.dev/og/posts/lKf7jUZk1.png
og:image:alt: I Run a Fleet of AI Agents Across Three Machines. Here's What Broke. - Kyle Jaejun Lee, KRAFTON
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# I Run a Fleet of AI Agents Across Three Machines. Here's What Broke. - Kyle Jaejun Lee, KRAFTON

**[AI Engineer](https://daily.dev/sources/aidotengineer)** · 9 min read · 0 upvotes · 0 comments

## Summary

A developer at KRAFTON shares hard-won lessons from running a fleet of AI coding agents across three machines (a MacBook and two Linux boxes). Starting with a single machine and tmux, the author hit a wall managing six simultaneous agent contexts and redesigned the system as a hierarchical organization (CEO/VP/manager/worker), each with scoped context stored in files on disk rather than model context windows. Key failures documented include agents doing work instead of delegating, tmux pane overflow, memory exhaustion, credential collisions, and laptop crashes wiping in-flight work. Solutions included file-based state for crash recovery, a review gateway for human approval, Git-based context sync across machines, per-machine directories to avoid conflicts, a unified SSH gateway on an always-on Linux box, and Discord bots as a single remote control. Remaining unsolved problems — consistency, tool portability, credential handoff, and resource scheduling — point toward Kubernetes as the next layer underneath the orchestration stack.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://www.youtube.com/watch?v=4kYl2_mqmnQ>

## Similar posts on daily.dev

- [What Breaks When Multi-Agent Systems Scale](https://daily.dev/posts/what-breaks-when-multi-agent-systems-scale-y4xkecht3) · DigitalOcean Community · 1 upvotes · 0 comments
- [My Coding Agents: Off My Laptop and Onto a Remote Server](https://daily.dev/posts/my-coding-agents-off-my-laptop-and-onto-a-remote-server-zxlgjxw5k) · Atomic Spin · 1 upvotes · 0 comments

---

Tags: [#kubernetes](https://daily.dev/tags/kubernetes), [#ai-agents](https://daily.dev/tags/ai-agents), [#claude](https://daily.dev/tags/claude)

[View this post on daily.dev](https://daily.dev/posts/i-run-a-fleet-of-ai-agents-across-three-machines-here-s-what-broke---kyle-jaejun-lee-krafton-lkf7juzk1)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"I Run a Fleet of AI Agents Across Three Machines. Here's What Broke. - Kyle Jaejun Lee, KRAFTON","url":"https://daily.dev/posts/i-run-a-fleet-of-ai-agents-across-three-machines-here-s-what-broke---kyle-jaejun-lee-krafton-lkf7juzk1","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/i-run-a-fleet-of-ai-agents-across-three-machines-here-s-what-broke---kyle-jaejun-lee-krafton-lkf7juzk1"},"datePublished":"2026-07-08T08:18:10.864Z","dateModified":"2026-07-08T08:18:34.707Z","description":"A developer at KRAFTON shares hard-won lessons from running a fleet of AI coding agents across three machines (a MacBook and two Linux boxes). Starting with a...","image":"https://i.ytimg.com/vi/4kYl2_mqmnQ/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/4kYl2_mqmnQ/sddefault.jpg","isAccessibleForFree":true,"articleSection":"AI Engineer","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"AI Engineer","logo":"https://media.daily.dev/image/upload/s--u5PucxNT--/f_auto/v1724338940/logos/aidotengineer","url":"https://daily.dev/sources/aidotengineer"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/i-run-a-fleet-of-ai-agents-across-three-machines-here-s-what-broke---kyle-jaejun-lee-krafton-lkf7juzk1","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"kubernetes,ai-agents,claude","timeRequired":"PT9M","video":{"@type":"VideoObject","name":"I Run a Fleet of AI Agents Across Three Machines. Here's What Broke. - Kyle Jaejun Lee, KRAFTON","description":"A developer at KRAFTON shares hard-won lessons from running a fleet of AI coding agents across three machines (a MacBook and two Linux boxes). Starting with a...","thumbnailUrl":"https://i.ytimg.com/vi/4kYl2_mqmnQ/sddefault.jpg","uploadDate":"2026-07-08T08:18:10.864Z","duration":"PT9M","url":"https://api.daily.dev/r/lKf7jUZk1","embedUrl":"https://www.youtube.com/embed/4kYl2_mqmnQ"}}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"AI Engineer","item":"https://daily.dev/sources/aidotengineer"},{"@type":"ListItem","position":3,"name":"I Run a Fleet of AI Agents Across Three Machines. Here's What Broke. - Kyle Jaejun Lee, KRAFTON"}]}
```

