Solomon's guide to

Cookin' with Gas

How one engineer runs a 24/7 multi-agent AI stack on bare metal. Opinionated. Dogfooded. Broken-and-fixed in production.

58 production-tested recipes for running long-lived AI agents in tandem with daily coding harnesses. Not a framework. A record of what is actually deployed, what broke, and how it was fixed.

Tonight's specials
Chapters
Chapter I

AI agent stack

Multi-model orchestration. One orchestrator, many models, escalation lanes. Most of these guides assume OpenClaw as the agent framework, but the patterns generalize.

13 recipes
Chapter II

Automation

Anything scheduled, hooked, or sandbox-wrapped. The decision tree for "where does this go" lives in cron-patterns.md - start there.

7 recipes
Chapter III

Self-hosted infrastructure

The homelab. Hypervisor decisions, container layout, network storage, off-host backup, integration with daily-driver desktop, and surviving upgrades.

7 recipes
Chapter IV

Security

Defense in depth across host, agents, network, and outbound boundary. Plus what to do when the agent does something it shouldn't.

6 recipes
Chapter V

Knowledge management

How durable knowledge flows: cards, indexes, handoffs, sync. The goal is "future-me can pick up cold."

6 recipes
Chapter VI

Hardware & host

The physical layer. Choosing the box, partitioning the disk, deciding what the host OS owns vs what gets virtualized.

3 recipes
Chapter VII

Tools

Index of tools shipped from this stack - MCPs, dashboards, helpers - and how they fit together.

5 recipes
Chapter VIII

Publishing

Reserved for docs about sanitizing and validating artifacts before they leave the host.

1 recipe
Chapter IX

Philosophy

The opinions. Why this stack is shaped the way it is. What I will not do. Why this body of work is a cookbook and not a tool.

4 recipes
Chapter X

Plans

1 recipe
Chapter XI

Skills

Public, sanitized skills pulled from a real always-on agent stack.

5 recipes