HN Showcase
Back to browse
From one Claude agent to a fleet – in five small steps

From one Claude agent to a fleet – in five small steps

by sermakarevich·May 21, 2026·2 points·0 comments
Visit ProjectView on HN

AI Analysis

●MidShip It

Useful shell script patterns, but just a workaround for API rate limits.

Strengths
  • •Pragmatic approach to parallelizing agent tasks without complex orchestration frameworks.
  • •Leverages existing GitHub issue discussions to validate the multi-agent pattern.
Weaknesses
  • •Relies entirely on manual shell scripting rather than a dedicated orchestration tool.
  • •Functionality is limited by the constraints of the underlying Claude Code CLI.
Target Audience

Developers using Claude Code who need to scale beyond single-agent limits

Similar To

LangGraph · CrewAI · AutoGen

Post Description

I was intrigued by an AMD issue on GitHub where Stella Laurenzo shared how the AMD team runs a fleet of 50 or so agents: https://lnkd.in/drueskiV. I wanted to get there myself, and I think I managed to. I can now run a fleet of coding agents while I'm away, burning through every token across my three Claude subscriptions. I can run data science experiments overnight in loops: analyze misclassifications, form a hypothesis, implement, run, analyze again. Agents pull tasks from a queue, add new tasks back to it, organize dependencies, and block tasks when they need my input. This article walks through my approach step by step.

https://github.com/sermakarevich/claude/tree/main/usage_patt...

Similar Projects