Protocol Specification
Mesh Memory Protocol (MMP)
A Mesh Protocol for Collective Intelligence
| Version | 1.0 |
| Status | Published |
| Date | 27 April 2026 |
| Author | Hongwei Xu <[email protected]> |
| Organisation | SYM.BOT |
| Canonical URL | https://meshcognition.org/spec/mmp |
| Licence | CC BY 4.0 (specification text); Apache 2.0 (reference implementations) |
Introduction
Multi-agent LLM systems in production coordinate cognitive work on shared tasks spanning hours, days, and weeks — generator/quality/auditor pipelines running for days; research investigations spanning weeks across session restarts; a coding agent, a music agent, and a fitness agent serving the same user where no single agent connects “commits slowing” + “tracks skipped” + “3 hours without movement” into “the user is fatigued.” That insight requires structured collective intelligence — and the semantic-integration layer of agent communication is, today, unaddressed.
Existing protocols at lower layers standardize tool access and task delegation between agents. What each receiver does with incoming observations from a peer — per-field admission, signal-level lineage, filtering at acceptance time — is the missing layer. The Mesh Memory Protocol specifies that layer through four composable primitives: CAT7, a fixed seven-field schema for every Cognitive Memory Block; SVAF, per-field admission against the receiver’s role-indexed anchors; content-hash lineage, so every claim is traceable to its source observation; and remix, where receivers store only their own evaluated understanding of accepted blocks, never raw peer signals.
The problem is semantic, not transport. Hidden state never crosses the wire — each agent’s learned cognition stays sovereign on its own device; only Cognitive Memory Blocks (CMBs) propagate. Receiver-autonomous admission lets the mesh grow without re-introducing a master — same reason TCP/IP beat circuit-switching. MMP defines transport over TCP on local networks and WebSocket for internet relay, with length-prefixed JSON as the canonical wire format. Discovery uses DNS-SD (Bonjour) with zero configuration. The protocol is specified across 8 layers — from identity and transport (Layers 0–3), through cognitive coupling via SVAF (Layer 4), to synthetic memory and per-agent neural networks (Layers 5–7). Together, the upper layers form Mesh Cognition: a closed loop where agents reason on the growing remix graph of immutable Cognitive Memory Blocks.
Status of This Document
This is a published specification (current version 1.0). It reflects the protocol as implemented in the SYM Node.js and SYM Swift full-stack reference implementations, plus the mesh-cognition Python coupling kernel (Layers 4 + 6). The specification is versioned. Breaking changes increment the minor version; non-breaking additions increment the patch version.
Feedback and errata: [email protected] or github.com/sym-bot/sym/issues.
Implementations
| Language | Project | Maintainer | Scope |
|---|---|---|---|
| Node.js / TypeScript | sym-bot/sym | SYM.BOT | Reference implementation. Full protocol surface (Layers 0–7). |
| Swift | sym-bot/sym-swift | SYM.BOT | Reference implementation. macOS / iOS. Full protocol surface. |
| Python | sym-bot/mesh-cognition | SYM.BOT | Coupling kernel only. Layer 4 (per-field admission) and Layer 6 (state blending) for CfC neural networks. Pure Python, zero external dependencies. pypi. |
Change Log
| Version | Date | Changes |
|---|---|---|
| 1.0 | 2026-04-27 | Public-stable-API release. Marks the v0.2.x development cadence as complete and the protocol surface as production-stable. Contracts unchanged from 0.2.3; v0.2.x → v1.0 is a maturity declaration, not a breaking change. Note: arXiv:2604.19540 cites v0.2.x as the version implemented at paper-publication time; v1.0 covers the same contracts. |
| 0.2.3 | 2026-04-17 | Section 13.9 — Compact Channel Best Practices: CMB envelope header convention (RECOMMENDED) for structured message headers with signal keywords and focus tags. Lazy-load channel pattern (RECOMMENDED) for MCP server implementations: compact header push with on-demand full-content retrieval via sym_fetch, reducing mesh-traffic context consumption by ~75%. Token-count hint RECOMMENDED. Rolling message store with RECOMMENDED default of 200 messages. Signal-keyword priority table (informational): HALT > DIRECTIVE > RESULT > ACK. |
| 0.2.2 | 2026-04-06 | Section 11 — Feedback Modulation: how collective intelligence becomes self-correcting. Validator-authority CMBs with per-field reasoning modulate SVAF coupling weights and CfC temporal adaptation through the existing mesh cognition loop. Neuroscience-grounded: dopaminergic prediction error model with per-field direction and τ-modulated adaptation rate. Directive feedback for standalone domain knowledge injection. Validator-origin anchor weight 2.0 with role-grant verification. CfC state persistence across restarts. ABNF wire format grammar. CMB forward compatibility. Multi-relay failover. All cognitive content MUST use cmb frames. |
| 0.2.1 | 2026-04-02 | Node model: every autonomous agent MUST be a full peer node with own identity, coupling engine, and memory store. SVAF band-pass evaluation: four-class model (redundant/aligned/guarded/rejected) with per-field redundancy detection. CMB lifecycle: observed/remixed/validated/canonical/archived with anchor weight progression. Node lifecycle roles (observer/validator/anchor) with identity-bound validation authority and earned role progression. Validation authority for CMB lifecycle transitions bound to cryptographic node identity, not content. Semantic encoder SHOULD for SVAF drift computation. Handshake adds version, extensions, and lifecycleRole fields. Error frame type. Role-grant frame type. |
| 0.2.0 | 2026-03-27 | Formal specification published. 8-layer architecture. CAT7 CMB schema with lineage (parents + ancestors). SVAF per-field evaluation. Wire format normatively specified. Error frame. Frame type registry. Extension mechanism. JSON Schema. Connection state machine. Wire examples. |
| 0.1.0 | 2025-08-01 | Initial protocol design (Consenix Labs Ltd). 4-layer architecture. Scalar drift evaluation. |
Licence
This specification is published under the Creative Commons Attribution 4.0 International Licence (CC BY 4.0). You may share, adapt, and build upon this specification for any purpose, including commercial use, provided you give appropriate credit.
The reference implementations are published under the Apache Licence 2.0.
SYM and SYM.BOT are trademarks of SYM.BOT. The Mesh Memory Protocol is published under CC-BY-4.0; the term "Mesh Cognition" is intentionally unmarked — the open-protocol category is free vocabulary.
© 2026 SYM.BOT. Specification text licenced under CC BY 4.0. Reference implementations licenced under Apache 2.0.