Research

Cognitive Memory Blocks

The structured semantic unit for multi-agent memory

Author: Hongwei XuVersion 1.0March 2026SYM.BOT Ltd

Core Insight

An AI agent observes: “user vibe coding with Claude for 8 hours straight, exhausted and losing focus, needs a break.” This single observation contains multiple dimensions — an activity, an energy state, a mood, an intent, a temporal context, a domain, and an urgency level. A fitness agent receiving this should absorb exhausted and needs a break while ignoring coding with AI. A music agent should absorb losing focus to adjust the playlist. Raw text gives them one cosine score that conflates everything. A Cognitive Memory Block decomposes the observation into 7 typed semantic fields — each independently comparable, each independently evaluable for cross-domain relevance.

What is a CMB

A Cognitive Memory Block is a set of typed field-vector pairs. Each field carries a symbolic text label (human-readable, for audit and retrieval) and a unit-normalised vector embedding (machine-comparable, for drift evaluation).

CMB = { (f, tf, vf) : f ∈ F }

Every CMB also carries: source agent, origin timestamp (when the event happened), stored-at timestamp (when the CMB was created), confidence, and provenance (fusion history with per-field drift scores).

Example

Input: “user vibe coding with Claude for 8 hours straight, exhausted and losing focus, needs a break”

FieldSymbolic LabelAffinity
activityvibe coding with ClaudeMedium
energylow energy: exhaustedHigh
moodlosing focusHigh
intentneeds breakMedium
context8 hour sessionMedium
domaincoding with AILow
urgencyhighMedium

The fitness agent sees: energy and mood are relevant (high synthesis affinity), domain is irrelevant (low affinity, sovereign). Per-field evaluation is impossible with a single flat embedding.

7 Fields, 3 Affinities

Fields are classified by synthesis affinity — how readily the field should be accepted across agent boundaries.

HIGH AFFINITY

Energy and Mood — universal signals. Every agent benefits from knowing the user’s physiological and emotional state. These fields cross all domain boundaries.

MEDIUM AFFINITY

Activity, Intent, Context, Urgency — selectively relevant. A fitness agent cares about activity; a knowledge agent may not.

LOW AFFINITY (SOVEREIGN)

Domain — agent-specific expertise that should not cross boundaries. A music agent’s BPM knowledge has no value to a fitness agent.

CMB vs. Raw Text

PropertyRaw TextCMB
ComparisonOne cosine score7 independent per-field scores
DriftSingle scalarPer-field drift showing WHERE it diverges
RetrievalKeyword / vector searchField-targeted: intent matches X AND issue mentions Y
AuditNoneFull provenance: anchors, weights, drift, fusion method
Agent handoffPrompt engineering per pairShared schema — any agent reads the same fields

Per-Agent Field Weights

Each agent configures which fields matter most to its domain. The schema is fixed; the weights are per-agent.

Agentactenemoodintctxdomurg
Claude Code1.51.20.81.5121
MeloTune0.81.520.81.21.50.8
MeloMove1.521.5111.51.5
Calendar0.50.80.5220.52

MeloTune weights mood at 2.0 — emotional state drives music selection. MeloMove weights energy at 2.0 — fatigue detection is its core function. Calendar weights intent, context, and urgency — scheduling intelligence.

Per-Agent Temporal Windows

The same signal has different temporal relevance depending on the receiver. Each agent defines its own freshness window.

30 min

MeloTune

Current mood for playlist — stale mood is wrong music

2 hours

Claude Code

Current session context — yesterday’s debugging is irrelevant

3 hours

MeloMove

Sedentary detection needs hours of context

24 hours

Knowledge

Daily digest cycle

Time-to-event

Calendar

Forward-looking — urgency increases as event approaches

How CMBs Fit the Stack

Agent observation → CMBEncoder (7 fields) → CMB
    → broadcast to mesh peers
    → SVAF evaluates per field → accept / reject
    → fused with local anchors → NEW synthesised CMB
    → feeds xMesh CfC → collective intelligence
    → insight → agent acts → remember() → loop

CMBs are the data structure. SVAF is the evaluation mechanism. xMesh is the collective intelligence. Three distinct layers, each independently defined.

Origin

Cognitive Memory Blocks were first formalised in the Mesh Memory Protocol (Consenix Labs, August 2025) with the CAT7 enterprise schema. The wellness/productivity schema and synthesis affinity classification were developed at SYM.BOT Ltd in late 2025 for production deployment across personal AI agents.

Cognitive Memory Blocks, Mesh Memory Protocol, and SVAF are research contributions of Hongwei Xu. Originally developed at Consenix Labs Ltd (2025). All research and intellectual property now held by SYM.BOT Ltd. © 2026 SYM.BOT Ltd.