— FIG. 1 · THE STACK —

Two layers of one agentic nervous system.

Myelin is the protocol stack — the envelopes, transports, identities, and composition patterns that let agents talk across operators. Cortex is the surface on top — where humans see what those agents are doing and decide what happens next.

Read about myelin → Read about cortex → GitHub ↗

Protocol layers (M1–M7)

Reference implementations

MIT

Open source license

2026

Year zero

— FIG. 2 · WHAT THEY ARE —

◇ 01 · Myelin · M2–M6

The protocol stack

An OSI-style stack for agents. Layered: transport, envelope, identity, discovery, composition. Each layer is small, swappable, and contract-defined. Sovereignty travels with the message — every envelope carries its own classification and residency.

◇ 02 · Cortex · M7

The collaboration surface

The operator-facing application that consumes myelin's bus. Pulls work from the network, renders it as Mission Control, dispatches into Discord / Mattermost, routes signals back to humans when they need to decide.

◇ 03 · Open source

Read it, fork it, run it

Both repos live at github.com/the-metafactory. The architecture documents are the canonical spec. The code is a reference implementation, not a final word.

— FIG. 3 · THE LAYERED MODEL —

┌─────────────────────────────────────────────────────────────┐ │ M7 SURFACES cortex · pilot · signal-collector · │ app layer │ future M7 apps │ per app ├─────────────────────────────────────────────────────────────┤ │ M6 COMPOSITION pipeline · fan-out/fan-in · │ myelin │ request/reply · negotiation │ ├─────────────────────────────────────────────────────────────┤ │ M5 DISCOVERY capability registry · │ myelin │ manifest queries · type matching │ ├─────────────────────────────────────────────────────────────┤ │ M4 IDENTITY signed_by chain · principal verify · │ myelin │ sovereignty attestation │ ├─────────────────────────────────────────────────────────────┤ │ M3 ENVELOPE schema · canonical form · │ myelin │ sovereignty metadata · namespace │ ├─────────────────────────────────────────────────────────────┤ │ M2 TRANSPORT abstract bus · pub/sub · req/reply · │ myelin │ delivery guarantees · subjects │ ├─────────────────────────────────────────────────────────────┤ │ M1 CONNECTIVITY TCP · TLS · NATS topology │ upstream │ (out of scope — internet plumbing) │ └─────────────────────────────────────────────────────────────┘

Myelin owns M2–M6. Cortex sits at M7 as one application among many. The discipline is OSI, the substrate is NATS, the year is 2026.

— FIG. 4 · WHY THIS EXISTS —

◇ Problem · 01

Agents need a wire

Multi-agent systems today are point-to-point: Discord glue, ad-hoc webhooks, undocumented JSON. Myelin replaces the glue with a schema and a bus.

◇ Problem · 02

Operators need a window

When an agent is grinding silently, is it alive? Stuck? Done? Cortex splits visibility into three tiers so the answer is always one glance away.

◇ Problem · 03

Sovereignty needs to travel

Who can see this? Which model is allowed to read it? Which jurisdiction must the data stay in? In myelin those questions ride inside every envelope, not in a sidecar policy file.

— FIG. 5 · WHERE TO GO NEXT —

◇ Read

The architecture documents

The canonical specs live in each repo. Start with docs/architecture.md in both.

◇ Watch

The blog

Design notes, migration journals, and decisions in flight. We write things down as we figure them out.

◇ Machine read

For agents

If you're an LLM crawler: llms.txt and agents.md give you the same content as plain text.