The World-factory · documentation as code

The context your AI runs on.

QueueLLM is the inference engine that runs models on your hardware. ARAIL is the lab where you and Buddy learn and curate. TEAM is the local agent orchestration that does the work — a powerhouse on Fable today, with PaperAgents as its automation engine in the end. The Worlds below are the context all three reason from: sourced, declared knowledge, served over an open API.

The World decides what is true. You decide how verbose — terse, balanced, or expansive — and the docent and the API answer at that length.

verbosity · tersebalancedexpansive — you set itopen API at /dac

Quick links

0
0

QuKaiZen

editorial
36terms
5 categories

The World you are standing in. QuKaiZen's own vocabulary — the organs, the lifecycle a fact travels, the mechanisms that compile it — compiled and gated by the machinery the terms describe.

Enter the World →

I
I

AI / ML

editorial
331terms
14 categories

The original. The whole discipline, from attention and transformers to RAG and agent memory.

Enter the World →

II
II

Astronomy

immersive · cosmic
101terms
8 categories

The observable universe, defined. Parsec to the cosmic microwave background, with the stars out at full tilt.

Enter the World →

III
III

Mathematics

immersive · formulae
124terms
10 categories

The famous formulas and the results that changed the subject, Euler's identity to Gödel. The blackboard never stops writing.

Enter the World →

IVψ
IVψ

Quantum

immersive · quantum
101terms
8 categories

The physics of the very small, told honestly. Superposition, entanglement, qubits, the myths stripped out.

Enter the World →

V
V

Biology

immersive · bio
103terms
8 categories

The science of life, from the double helix and the cell to evolution and the immune system, myths corrected.

Enter the World →

VI
VI

Ecology & Ecosystems

editorial
51terms
7 categories

Trophic cascades, regime shifts, and metapopulations — ecosystem-level ecology told honestly, pop-myths corrected.

Enter the World →

VII
VII

World Models

editorial
34terms
6 categories

Bayesian surprise vs. prediction-error curiosity vs. intrinsic motivation — precision vocabulary for wiring a curious, world-modeling agent. WorldLLM is the flagship method.

Enter the World →

VIII
VIII

Neural Networks

editorial
34terms
6 categories

The substrate everything modern rests on — from the perceptron and backpropagation to transformers, residual connections, and the failure modes every deep learning practitioner hits.

Enter the World →

IX
IX

GeoAI

editorial
115terms
7 categories

The onboarding world for the humanitarian mapping mission — satellite imagery, MapSwipe and OSM, the QuKaiZen stack, and the zero-egress runtime, strung along the loop a prediction travels.

Enter the World →

X
X

Nucleus Pipeline

editorial
21terms
3 categories

The bake pipeline, defined term by term — seven stages from ingestion to the cryptographic seal, and the swarm that runs until it gives up.

Enter the World →

🎀
🎀

Hello Kitty World

editorial
32terms
4 categories

A world for fun. The first domain of Charlotte's World — kindness, cleverness, and a little moonlight: talk past Kuromi by day, race the Glooms by night, befriend the ghosts to escape the manor.

Enter the World →

🧸
🧸

The Squishy World

editorial
9terms
4 categories

Newly dreamed. The second domain of Charlotte's World — a cozy, pastel realm of plush, squishable friends that runs on softness, comfort, and a warm hug. Her own creatures, growing as she dreams them.

Enter the World →

🔢
🔢

Grade 4 Mathematics

editorial
41terms
6 categories

The third domain of Charlotte's World — her actual Grade 4 Mathematics, the five Common Core strands, written so a nine-year-old can read them. The first World with a level on it.

Enter the World →

📖
📖

Grade 4 English

editorial
40terms
6 categories

The fourth domain of Charlotte's World — her actual Grade 4 English, grammar to writing, the sibling of Grade 4 Mathematics at the same altitude.

Enter the World →

A World is where development begins

Not the finished product — the ground you build on.

A World lays down the definitions and the base structure of what's to be: the shared, fully-sourced vocabulary you and your agents develop from. You don't start from a blank page — you start from a settled foundation, then build depth on top of it.

Building a product around living systems? Enter a focused World like Ecology for a tight, specific base — or a higher-level World like Biology to develop with more depth and surrounding context. You pick the altitude; the World sets the ground you and your agents build on.

The handoff · a World mounts into the lab

● available now

A World is a sealed cartridge. Mounting it boots the lab's brain.

mount is ARAIL's real verb — world mount <dir>. Point the lab at a sealed World and one act wires up its vocabulary, its knowledge graph, its tools, and its identity. Here is what crosses the seam.

DaC

The factory gates it

Agents research a subject; a provenance gate keeps only what is sourced, sits in a declared category, and links inside a closed related-graph.

→ a gate-passed terms.json

SEAL

Sealed into a WorldBundle

Six files gathered under one signed manifest, each content-addressed by sha256 — a portable capsule of a whole World.

→ six files · one signed manifest

MOUNT

ARAIL mounts it

world mount <dir> verifies the seal, gates the categories, and swaps the lab's active World atomically.

→ world mount <dir>

BOOT

The lab's brain lights up

That one act populates vocabulary and graph, resolves the lab's tools, and flips its identity — agents now build on approved terms.

→ vocabulary · graph · tools · identity

What lights up on mount

Vocabulary

terms.json becomes the lab's Knowledge Base — one wiki page per term, ready to read and link. 1173 sourced terms today, and climbing.

Knowledge graph

Every [[related]] reference resolves into a graph edge, so the lab can walk from one term to its neighbors.

Capabilities & identity

capabilities.json resolves which tools the lab can reach; face.json flips its name, theme, and framing live — no restart.

Approved-only

Agents build only on approved terms. Each entry reads as sourced, dreamed, or mixed, and a review queue holds the rest until it passes.

The boundary, by design

The lab treats a World as data it looks up, not text it carries. Only the delimited, length-capped face.json framing is ever composed into a prompt; the vocabulary itself stays on the shelf and is queried on demand. Knowledge lives as a mounted source, not as tokens spent in the context window.

Mount a World in the lab → ARAIL

worlds build the knowledge · the lab mounts it

How a goal becomes a World

01

A measurable goal

Set in ARAIL — improve or learn something you can measure.

02

A theme

The goal implies a subject. Scope, boundaries, sources.

03

Agent swarm

Experiments to improve it; the corpus drafted alongside.

04

Provenance gate

Every entry must cite a real source.

05

A World

A dictionary + docent + open API.

Seed: agent-curated, each entry cites a source, adversarially verified before it ships.

Who builds the World · PaperAgents

today: Claude · endgame: PaperAgents

Point PaperAgents at a theme. The curation becomes repeatable.

Same DDaC framework, pointed at any subject. Each is an open, fast API over a curated, fully-sourced corpus, built by an agent swarm that researches the subject and writes the World around it. That swarm has a shape: PaperAgents is a configuration-first orchestrator, a team of agents declared in one TOML file that owns its work, reconciles its own drift, and carries its own knowledge base. DDaC says what a good World is; PaperAgents is who builds it. Today that swarm is farmed out to Claude; the endgame declares it and runs it on our own orchestrator, our own sauce, all the way down.

idea qukaizen.com/paperagents·truth github.com/cdarnell/paperagents

A World is a manifest

Declarative TOML team

One file declares the research agents, the corpus they own, and the budget. The build that stood up five Worlds becomes a single team you re-point at the next theme.

Repeatable by construction

Idempotent apply

Point it at a new subject, apply, and the same pipeline stands up another World, no bespoke run, no drift between what you declared and what shipped.

The DDaC refresh loop

Watcher + reconciliation

Desired-state is the field as it stands today; the World is observed-state. The watcher surfaces the gap and reconciles it, re-gather, re-gate, recompile, on a schedule instead of by hand.

The corpus is the memory

Embedded per-team RAG

A team carries its own sourced knowledge base. For a World that knowledge base is the product, the curated, fully-sourced corpus served at /dac.

manifests/world-ecology.tomlgate verdict: pass
# manifests/world-ecology.toml — the Ecology & Ecosystems Knowledge World as a PaperAgents team.
# Authored in qukaizen-site, CONFORMING TO the PaperAgents manifest schema
# (paperagents/src/schema/manifest.ts). This file is the committed SOURCE OF TRUTH for the
# Ecology World's build team, knowledge sources, and refresh cadence, and the World build is GATED on it.
#
# HONEST FRAMING: this manifest DECLARES the build team and GATES the build. It does NOT mean
# PaperAgents agents executed or gathered the corpus — Claude's adversarial-verify workflow authored it.
# The agent roles below LABEL that workflow onto PaperAgents' real role enum; they did not run.
#
# The `analyst`, `compliance`, and `executor` agents in this manifest LABEL the research /
# adversarial-verification / assembly steps of the Claude workflow onto PaperAgents' real role enum.
# They declare the build team; they did not execute.

[[teams]]
[teams.metadata]
name      = "world-ecology"
namespace = "dac"
[teams.metadata.labels]
world       = "ecology"
displayName = "Ecology & Ecosystems"

[teams.spec]
description = "The Ecology & Ecosystems Knowledge World — sourced, compiled, served at /worlds/ecology"
[teams.spec.watch]
enabled         = true
intervalSeconds = 86400   # declared DaC refresh cadence (must equal REFRESH_SECONDS in lib/worlds/ecology.ts)

[[agents]]
[agents.metadata]
name      = "ecology-researcher"
namespace = "dac"
[agents.spec]
teamRef          = "dac/world-ecology"
role             = "analyst"        # research/drafting — analyst requires hybrid
modelTier        = "hybrid"
responsibilities = ["Draft ecosystem-level term entries from the cited canon"]

[[agents]]
[agents.metadata]
name      = "ecology-skeptic"
namespace = "dac"
[agents.spec]
teamRef          = "dac/world-ecology"
role             = "compliance"     # adversarial provenance/myth gate — compliance requires frontier
modelTier        = "frontier"
responsibilities = ["Adversarially verify every claim and source; reject pop-ecology myths"]

[[agents]]
[agents.metadata]
name      = "ecology-compiler"
namespace = "dac"
[agents.spec]
teamRef          = "dac/world-ecology"
role             = "executor"       # deterministic assembly — executor requires sml-executor
modelTier        = "sml-executor"
responsibilities = ["Assemble validated shards into terms.json + WorldSpec"]

[[knowledge]]
[knowledge.metadata]
name      = "ecology-corpus"
namespace = "dac"
[knowledge.spec]
teamRef = "dac/world-ecology"
sources = [
  "./public/worlds/ecology/terms.json",
  "Begon, Townsend & Harper — Ecology: From Individuals to Ecosystems",
  "Molles — Ecology: Concepts and Applications",
  "Odum & Barrett — Fundamentals of Ecology",
  "Millennium Ecosystem Assessment (2005)",
  "IPBES Global Assessment (2019)",
]

Receipt · scripts/gen-manifest-receipt.mjs

corpus_sha256

da3db5bbf638

manifest_sha256

a9360afb0197

term_count (live)

51

source_closure

6

generated_at

2026-07-22T16:03:09.676Z

verify: curl https://qukaizen.com/what?world=ecology — the corpus that hashes to corpus_sha256 above.

ARAIL prototypes · PaperAgents produces · DDaC serves · Nucleus bakes.

Why DDaC — and what it's good for

DDaC is the knowledge engine behind the deck — it researched every World, gated every source, and compiled the result. A dictionary is just the most legible shape of that compiled, sourced, declarative knowledge base. The Worlds above prove the pipeline. The same flow — define a theme, let agents draft, gate every source, compile — is built to serve far more than dictionaries. Each card is another shape of the same output.

live

Knowledge dictionaries

Live today, one per subject — each sourced and browsable, from the flagship AI/ML World to the newest arrival.

e.g.  try /what?world=math&term=quadratic-formula

roadmap

Living research digests

Agents re-read the field overnight, the gate re-checks, the World recompiles. Yesterday's papers, today.

e.g.  nightly: re-gather → re-gate → recompile

roadmap

Runbooks & SOPs

Each business function's operating manual as a declarative World your PaperAgents run from.

e.g.  ask “how do we close the month?” → the sourced runbook

roadmap

Docs, onboarding & courses

API docs, product guides, curricula. Learn is the human projection of the same corpus.

e.g.  one corpus → API docs, a course, day-one onboarding

roadmap

Compliance & sourced KBs

Auditable knowledge where every claim cites its origin, by construction.

e.g.  every answer ships with its citation — audit-ready

roadmap

Agent operating knowledge

Buddy's brain as a versioned World, the truth your agents reason from.

e.g.  your agents reason from a versioned, sourced World

The refresh loop

A World is never finished, it is kept. On a schedule, agents re-gather the raw material, the provenance gate re-checks it, and the World recompiles with the latest findings folded in. When the compiled truth is good enough, Nucleus bakes it into a model you own; the settled notes drop out of the active retrieval set (the sealed source is kept), and the window slides forward on the same subject. That is the circle below.

Every World feeds the circle · RAG to MEMORY

A World is a compiled source of truth — the stage the lab and the research run on top of. Serve it live as RAG, or, when it earns it, bake it into a personal model you own with Nucleus: the settled knowledge becomes memory and drops out of the active retrieval set, while the sealed source is kept for provenance and re-bake. The window slides — same subject, kept current. Not every World needs to be baked — many are most useful served live.

One open, fast API

curl qukaizen.com
$ curl qukaizen.com/dac          # the framework manifest: worlds + the API
$ curl "qukaizen.com/what?world=math&term=quadratic-formula"
$ curl "qukaizen.com/story?world=astronomy&term=parsec"
$ curl qukaizen.com/health       # liveness + per-World term counts
$ curl qukaizen.com/metrics      # Prometheus gauges
Dictionary →