01 / INTENT
Intent
LLM gives intent. The agent proposes through typed intents; proposals may be wrong — that is fine.
Deterministic systems meet atmospheric poetry.
Building a World OS where AI agents are first-class citizens — not tools.
💮 verified 2026-08-15 · this page holds true
01 / The World OS
An AI-native World OS for simulated interactive worlds — an embodied AI runtime that looks like a game engine.
💮 version 0.7.0 · verified 2026-08-15
01 / INTENT
LLM gives intent. The agent proposes through typed intents; proposals may be wrong — that is fine.
02 / TRUTH
Engine gives truth. Validation runs deterministic, contract-checked simulation. Proposals either survive or are rejected.
03 / CONTROL
Editor gives human control. Branch and merge for multi-agent worlds. No session context → no mutation.
04 / TRUST
Evidence gives trust. Proven, reproducible, rollback-able evidence. Nothing is believed on faith.
02 / Agents & Simulation
Agents live inside verifiable physics and scenarios — not in loose text. Each has identity, capabilities, a budget, and an audit trail. The Semantic Mirror gives them sight; the Agent Session gives them citizenship: no session context, no mutation.
A rainy world under simulation. An early idea — mysticism, weather, and care. Itrains stays poetry; Khan Engine stays engineering.
03 / Non-goals
This page is the first citizen of its own philosophy.
04 / Transmissions