— ARS · MAGNA —

O P U S

A  multi-agent  swarm  architecture
for  collective  reasoning

Scroll

§1 — Manifesto

Opus is not a model. It is a colony.

A single language model, however large, reasons in one voice. It produces a stream of plausible tokens, defends them, and moves on. It cannot meaningfully disagree with itself, cannot triangulate, and cannot be falsified except from outside.

We replace that lonely soliloquy with a structured swarm. Three concentric tiers — Scouts at the perimeter, Workers in the middle, a Hive Core at the centre — coordinate not by speaking to each other but by writing typed records to a single shared substrate: the Blackboard, an append-only event log. The environment is the conversation.

When the colony has deliberated enough, three stages of consensus run: weighted Borda aggregation across Worker rankings, an LLM-as-Judge adjudication on near-ties, and a Verifier pass that attempts to falsify the chosen answer. If verification fails, the swarm re-deliberates with the falsification as a new constraint. The loop is bounded. The colony does not lie about its certainty.

Solve et coagula. Dissolve a single mind into many; recombine the many into one well-considered answer. That is the Great Work.

§2 — Three principles

The Beehive Brain

I.

Parallel Exploration

Many Scouts read the world at once. None depend on the others; all write to the same Blackboard. Coverage, not coordination, is the unit of progress.

II.

Stigmergic Memory

Agents do not message each other. They modify a shared environment — the Blackboard — and respond to its state. Communication is a side effect of work.

III.

Consensus Synthesis

Three stages: Borda aggregation, Judge adjudication, Verifier falsification. The colony surfaces what survives, attached to its provenance and confidence.

§3 — Architecture

The Topology

Hover or focus a node

§4 — A swarm in motion

Live Swarm

REAL-TIME OPUS LLM SWARM · LET THE COLONY WORK

HiveResearcher αResearcher βCritic αCritic βSynthesiserVerifierScout 0Scout 1Scout 2
— colony at rest —
00:00.000
$0.0000
— transcript —
0 records
press Begin Deliberation to wake the colony

§5 — Philosophy

The Great Work

Why a swarm?

A colony introspects. A lone agent does not. The cheapest unit of useful disagreement is two agents reading the same Blackboard and producing different syntheses. Once you have that, you can rank, you can adjudicate, you can falsify. Cognition becomes legible.

“Dissolve the one mind into many. Recombine the many into one well-considered answer.”

Lineage

OPUS stands on three traditions: Ramon Llull’s Ars Magna (1305) — combinatorial generation under a falsifier; Hearsay-II (CMU, 1971–1976) — the first blackboard architecture for cooperative cognition; and stigmergy (Grassé, 1959) — the principle that termites, and now agents, coordinate by modifying their environment.

Ars Magna

We do not claim novelty in the parts. We claim attention to the whole — combinatorial generation, shared substrate, stigmergic coordination, bounded falsification — applied to large language models with engineering discipline. Solve et coagula. The work continues.

§6 — The Ouroboros

Autogenesis

The Ouroboros — the colony that builds itself
The Ouroboros · the work that creates the workman

OPUS was not built top-down by a single mind.
It was built — and continues to be built — by the swarm it is.

The architect does not propose features. They pose questions. The colony deliberates. Scouts gather, Workers argue, the Verifier attempts to falsify, the Hive Core surfaces a verdict. Only then is the verdict transcribed into code, into prose, into the public site.

Every architectural choice, every agent role, every sigil in the codex, every commit in the log — was first deliberated by the colony, then made by the colony, then verified by the colony. The work belongs to the work.

“The serpent eats its tail. The loop is sealed. Nothing leaves that was not first verified within.”

§7 — Built in public

Build Log

In the making for fifteen days· the work continues

TBD

Day N — the real swarm in the browser

opus-core deployed on Modal. A Vercel API route proxies via Server-Sent Events. The LiveSwarm component begins consuming actual Records from a live deliberation against the Anthropic API. The demo becomes the product. Cost is honest, provenance is downloadable, every visitor can pose the colony a real question.

12 MAY

Day 15 — nav, lore, cinematic demo, contract

Four shipments in one day. Top-left nav (OpusAI · Whitepaper · Team) persisting across every page. New routes — /whitepaper (full readable spec) and /team (anonymous lore for the architect). LiveSwarm upgraded from static mockup to interactive cinematic demo: animated topology, live transcript, climbing cost ticker, per-letter answer reveal. Contract address added to the hero with click-to-copy. The project finally feels like a thing strangers can land on and understand.

11 MAY

Day 14 — opus-core ships, the site goes live

opus-core finished end-to-end: Blackboard, eight agent roles, Hive orchestrator with verification loop, full provenance ledger, JSONL trace output. 18/18 unit tests pass. opus-web pushed to Vercel — which took an embarrassing number of broken deploys before discovering the deployment-protection wall and a framework-detection misfire. Site finally went live in the early hours.

10 MAY

Day 13 — the sphere in Three.js

Built the armillary sphere in React Three Fiber. Wireframe globe, concentric meridian rings, a beaded equatorial band, gold ember at the centre on a slow heartbeat pulse. GLSL fragment shader for the storm-cloud background. Mouse parallax tilts the whole sphere toward the cursor. First moment the brand felt fully alive.

9 MAY

Day 12 — Windows tooling hell

Tried to set up the dev environment on Windows. Python wasn't installed. PowerShell's default execution policy silently blocked every npm script. uv ran for ten minutes without output. Lost the better part of the day to environment friction. Final answer: winget for everything, bash for npm, and a documented setup so the next contributor doesn't pay this tax.

8 MAY

Day 11 — whitepaper week

Wrote the whitepaper properly — nine sections, around 1200 words. Then the architecture deep-dive (engineer companion), a strict glossary, and the lineage essay walking through three rooms: Llull's chamber in Mallorca, Erman and Lesser's lab at Carnegie Mellon, Grassé's termite mound. The lineage piece took the longest. Borges-tinged on purpose.

7 MAY

Day 10 — the site is a grimoire

Started sketching the public site. The temptation was a dry technical doc. The decision: build it like a grimoire. Armillary sphere as the centrepiece. Cream-on-black, Cinzel and Cormorant, monastic spacing. It should feel like the manuscript of an order — not a startup landing page.

6 MAY

Day 9 — tests and provenance

Built the test suite — eighteen unit tests covering the Blackboard, consensus math, and Hive orchestrator. Added the provenance ledger with honest USD cost tracking against real Anthropic pricing. No virtual tokens, no crypto handwaving, no theatre — just dollars. Memory adapters (vector, graph) left as interfaces; concrete backends are Phase β work.

§8 — Stack

Materials

claude-opus-4-7
Workers, Judge, Verifier
ACTIVE
claude-sonnet-4-6
Scouts, lightweight critique
ACTIVE
asyncio + anyio
Concurrency runtime
ACTIVE
pydantic v2
Strict typing on every Record
ACTIVE
structlog (JSON)
Structured observability
ACTIVE
typer
CLI surface (`opus query …`)
ACTIVE
hatchling
Packaging backend
ACTIVE
pytest + pytest-asyncio
Test suite
ACTIVE
Next.js 14 + Three.js + GSAP
This site
LIVE
Qdrant
Vector memory (interface stubbed)
PLANNED
Neo4j
Graph memory (interface stubbed)
PLANNED
Redis Streams
Distributed Blackboard backend
PLANNED
OpenTelemetry
Distributed tracing
PLANNED

— Initiation —

Join the Work

Daily builds are broadcast in public. The whitepaper is the source of truth. Early access is by request.