LifeOS Foundations
The 17 Founding Principles.
Every subsystem in LifeOS answers to these. They predate the code, and when a design question gets hard, the answer is usually already in one of them. Pick a card for the full story.
Principles · 17
№ 1 · Core Philosophy
Clear Thinking + Prompting is King
Structured thinking and precise prompts create deterministic, reliable AI systems
№ 2 · Architecture
Scaffolding > Model
The infrastructure around the model matters more than the model itself
№ 3 · Core Philosophy
As Deterministic as Possible
Reduce randomness through code, templates, and structured workflows
№ 4 · Technical
Code Before Prompts
Write deterministic code first, wrap it with prompts only when needed
№ 5 · Technical
Spec / Test / Evals First
Define success criteria before building anything
№ 6 · Architecture
UNIX Philosophy
Small, composable tools that do one thing well
№ 7 · Technical
ENG / SRE Principles
Production-grade reliability, observability, and maintainability
№ 8 · Architecture
CLI as Interface
Command-line first, with keyboard shortcuts and automation
№ 9 · Architecture
Goal → Code → CLI → Prompts → Agents
Clear hierarchy from objectives to implementation
№ 10 · Extensibility
Meta / Self-Update System
LifeOS can analyze and improve itself systematically
№ 11 · Extensibility
Custom Skill Management
Modular capabilities you can install, customize, and extend
№ 12 · Architecture
Custom History System
Unified observation and context persistence across all interactions
№ 13 · Extensibility
Custom Agent Personalities
Specialized AI personas with unique expertise and voices
№ 14 · Core Philosophy
LifeOS is the Life Operating System
An AI harness that moves you from current state to ideal state—every subsystem serves that one loop
№ 15 · Extensibility
Customization of an Agentic Platform for Achieving Your Goals
Generic out of the box, yours after setup—the platform molds to your goals, not the other way around
№ 16 · Core Philosophy
Science as Cognitive Loop
Hypotheses, falsifiable claims, evidence before belief—the scientific method applied to getting things done
№ 17 · Core Philosophy
Permission to Fail
A failed probe that teaches beats a polished guess—the system records failures and converts them into gates