Back to feed
Dev.to
Dev.to
6/27/2026
The original title is "We Run 9 AI Agents on 2 CPU Cores and 3.6GB RAM: The Engineering Memoir"

The original title is "We Run 9 AI Agents on 2 CPU Cores and 3.6GB RAM: The Engineering Memoir"

Original: We Run 9 AI Agents on 2 CPU Cores and 3.6GB RAM: The Engineering Memoir

Short summary

A Chinese fitness gym runs 9 production AI agents on 2 CPU cores and 3.6GB RAM using DeepSeek APIs and filesystem-based messaging instead of Kubernetes. The engineering post details practical architecture: identity files for agent configuration, cron+heartbeat monitoring, and Node.js/Python framework integration. Key lesson: orchestration quality matters more than compute density.

  • •9 production agents running on 2-core Ubuntu box with 3.6GB RAM—no GPU cluster required
  • •Uses DeepSeek V4 API (Pro for strategic agents, Flash for operational) to offload LLM computation
  • •Simple filesystem and cron-based orchestration outperforms complex event buses at this scale

Generated with AI, which can make mistakes.

#ai-agents#ai-tools#open-source
Read full article at Dev.to

Is this a good recommendation for you?

Comments

Failed to load comments. Please try again.

Explore more

The original title is: "9 AI Agents, 2 CPU Cores, One Gym: The 3-Layer Architecture"
Dev.to
The original title is: "107 Days in Production with 9 Autonomous Agents: Infrastructure Bugs, Not AI Failures"
Dev.to
Building an Autonomous Multi-Agent System with CrewAI: Config-Driven Architecture, KPI Optimization, and Day-1 Production Results
Dev.to
How I Run a 50-Agent AI Workforce on a Single 6GB GPU
Dev.to