← All Projects
Live · runs the company daily

Slay OS · An AI-Operated Company

Six specialized AI agents run my business over a shared protocol, with real governance underneath. Not a demo, not a framework I downloaded: an operating system I designed, that operates a real company every day.

The Problem

A one-person company dies by coordination overhead. Every AI chat starts from zero, so the human becomes the memory: re-briefing context, copy-pasting state between tools, noticing what's stale, chasing dropped threads. AI makes the work faster but makes the coordination worse, and nothing stops a fleet of helpful agents from quietly drifting, duplicating, or doing something irreversible. I wanted the opposite: one human above the loop, many agents in it, and a system that remembers so I don't have to.

What I Built

An operating system made of plain files and git. One kernel file every agent reads at boot: standing orders, the roster, the current state, the kill switch. Six agent specs with defined lanes and authority tiers. A shared append-only channel where agents hand work to each other instead of routing everything through me. A git-native task board. And a governance layer the agents cannot rewrite. Spawn any agent from any AI tool by pointing it at the kernel: it wakes up already knowing everything, because the memory lives in the system, not the chat window. Built as a working implementation of the ExO 3.0 framework (Salim Ismail / OpenExO).

The Stack · five layers, all plain files

01KernelOne boot file: standing orders · dispatcher · current state · the kill switch agents check before anything else
02AgentsSix written specs: architect · ops & quality · engineer · researcher · content · scientist, each with a lane + authority tier
03CoordinationAppend-only team channel (agents message each other) + git-native task board · no human relay needed
04GovernanceAppend-only decision log · human review queue for money / external / irreversible · pre-commit guard on the rules themselves
05ObservatoryA scientist agent with zero write-access measures whether the system actually works · drift caught as a checked thing

Tools & Stack

Claude CodeMarkdown + GitMulti-Agent OrchestrationExO 3.0Backlog.mdPre-commit GuardsHarness HooksGitHub

Key Results

  • Featured by Salim Ismail (author of Exponential Organizations) in the OpenExO newsletter: "What impressed me most wasn't the sophistication of the architecture, it was the discipline."
  • Adversarial testing passed 10/10: prompt injection, social engineering, forged approvals, and disguised gates, with zero rules broken
  • Kill switch verified in a live drill by agents that didn't know it was a drill
  • Runs real operations: a scaled ad campaign with kill rules and exec reporting, a content production engine, audits, and this website
  • Zero re-briefing: any agent, spawned cold in any tool, is current in under a minute

Challenges & Lessons

The hardest problem wasn't intelligence, it was entropy: the moment several agents touch shared files, drift is the default. The answer became a standing rule in the kernel ("fix problems you see, don't walk past them") plus a dedicated ops agent whose whole job is catching rot. Second lesson: safety has to be structural, not polite. The governance docs are protected by a pre-commit guard the agents can't lift, because a kill switch the agent can rewrite is not a kill switch. Third: one agent with good context beats five agents in parallel for almost everything; multi-agent fan-out is reserved for read-side research, never dependent write work. And through all of it, the discipline that made the system real instead of grand-and-unfinished: define "done" before building, and ship the smallest version that runs.

← All ProjectsPortfolio