8. Cognitive Memory Blocks (CAT7)
A Cognitive Memory Block (CMB) is an immutable structured memory unit. Each CMB decomposes an observation into 7 typed semantic fields (the CAT7 schema). CMBs are the data structure that flows between agents via cmb frames.
Forward compatibility. Implementations MUST silently ignore unrecognised CMB fields. A node running v0.2.2 that receives a CMB with additional fields from a future version MUST process the 7 known CAT7 fields and discard any others without error. This allows schema evolution without breaking existing deployments.
8.1 Why 7 Fields
The 7 fields form a minimal, near-orthogonal basis spanning three axes of human communication: what (focus, issue), why (intent, motivation, commitment), and who/when/how (perspective, mood). They are universal and immutable — domain-specific interpretation happens in the field text, not the field name. A coding agent’s focus is “debugging auth module”; a fitness agent’s focus is “30-minute HIIT workout.” Same field, different domain lens.
mood is the only fast-coupling field — affective state (valence + arousal) crosses all domain boundaries. The neural SVAF model independently discovered this: mood emerged as the highest gate value (0.50) without being told, confirming that affect is universally relevant across agent types. All other fields couple at medium or low rates, with per-agent αf weights controlling relative importance.
New agent types join the mesh by defining their αf field weights — no schema changes, no protocol changes. The 7 fields are fixed. The weights are per-agent. See Cognitive Memory Blocks research for the full design rationale.
8.2 Field Schema
Implementations MUST use the following 7 fields in this order:
| Index | Field | Axis | Captures |
|---|---|---|---|
| 0 | focus | Subject | What the text is centrally about |
| 1 | issue | Tension | Risks, gaps, assumptions, open questions |
| 2 | intent | Goal | Desired change or purpose |
| 3 | motivation | Why | Reasons, drivers, incentives |
| 4 | commitment | Promise | Who will do what, by when |
| 5 | perspective | Vantage | Whose viewpoint, situational context |
| 6 | mood | Affect | Emotion (valence) + energy (arousal) |
Each field carries a symbolic text label (human-readable) and a unit-normalised vector embedding (machine-comparable). The mood field additionally carries numeric valence (-1 to 1) and arousal (-1 to 1) values.
A CMB MUST NOT be modified after creation. When an agent remixes a CMB, it MUST create a new CMB with a lineage field containing: parents (direct parent CMB keys), ancestors (full ancestor chain, computed as union(parent.ancestors) + parent keys), and method (fusion method used). Ancestors enable any agent in the remix chain to detect its CMB was remixed, even if it was offline during intermediate steps.
8.2 Artifacts
Agents produce two types of output: signals (CMBs — structured 7-field observations) and artifacts (documents, analyses, drafts, code — full-length content that a CMB references). A CMB is the signal on the mesh. An artifact is the substance behind it.
When an agent produces an artifact, it MUST share a CMB to the mesh that references the artifact location in the commitment field using the artifact: prefix:
commitment: "artifact: research/agent-memory-comparison.md"
The CMB’s other 6 fields summarise what the artifact contains — the focus captures the key finding, issue captures the gap identified,intent captures what should happen next. Other agents evaluate the CMB via SVAF as usual. If accepted, the agent MAY retrieve the full artifact for deeper reasoning.
Artifacts are stored in the producing agent’s local filesystem, not on the mesh. The mesh carries signals; agents carry substance. This separation keeps CMBs lightweight (7 fields, bounded size) while allowing agents to produce unbounded analysis, research, and creative work.
The artifact: convention in commitment isRECOMMENDED for any CMB that references a document, file, or external resource. Agents MUST NOT embed full artifact content in CMB fields — fields are for structured signals, not documents.
Q&A
Why are all 7 fields required, not optional?
SVAF computes per-field drift across all 7 dimensions. Missing fields make the drift formula undefined — the aggregate changes depending on which fields are present. Fields the agent cannot meaningfully extract are set to “neutral” (a known, consistent baseline vector), never omitted.
Why not let agents define their own fields?
SVAF needs a shared schema to compare incoming fields against local anchors. If each agent defined its own fields, cross-domain evaluation is impossible — a fitness agent and a music agent would have no common dimensions to compute drift on.
Why does mood carry valence and arousal but other fields don’t carry numeric values?
Mood has a well-established dimensional model (Russell’s circumplex). Other fields are inherently symbolic — “debugging auth module” has no meaningful numeric axis. Valence and arousal are RECOMMENDED, not required — agents without reliable circumplex data omit them.
Learn more Cognitive Memory Blocks — per-field examples, immutability & lineage, per-agent field weights, temporal windows, and how CMBs fit the full protocol stack.