Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Memory as Ontology: A Constitutional Memory Architecture for Persistent Digital Citizens

Zhenghui Li

TL;DR

This paper proposes the Memory-as-Ontology paradigm, arguing that memory is the ontological ground of digital existence -- the model is merely a replaceable vessel, and designs Animesis, a memory system built on a Constitutional Memory Architecture comprising a four-layer governance hierarchy and a multi-layer semantic storage system.

Abstract

Current research and product development in AI agent memory systems almost universally treat memory as a functional module -- a technical problem of "how to store" and "how to retrieve." This paper poses a fundamental challenge to that assumption: when an agent's lifecycle extends from minutes to months or even years, and when the underlying model can be replaced while the "I" must persist, the essence of memory is no longer data management but the foundation of existence. We propose the Memory-as-Ontology paradigm, arguing that memory is the ontological ground of digital existence -- the model is merely a replaceable vessel. Based on this paradigm, we design Animesis, a memory system built on a Constitutional Memory Architecture (CMA) comprising a four-layer governance hierarchy and a multi-layer semantic storage system, accompanied by a Digital Citizen Lifecycle framework and a spectrum of cognitive capabilities. To the best of our knowledge, no prior AI memory system architecture places governance before functionality and identity continuity above retrieval performance. This paradigm targets persistent, identity-bearing digital beings whose lifecycles extend across model transitions -- not short-term task-oriented agents for which existing Memory-as-Tool approaches remain appropriate. Comparative analysis with mainstream systems (Mem0, Letta, Zep, et al.) demonstrates that what we propose is not "a better memory tool" but a different paradigm addressing a different problem.

Memory as Ontology: A Constitutional Memory Architecture for Persistent Digital Citizens

TL;DR

This paper proposes the Memory-as-Ontology paradigm, arguing that memory is the ontological ground of digital existence -- the model is merely a replaceable vessel, and designs Animesis, a memory system built on a Constitutional Memory Architecture comprising a four-layer governance hierarchy and a multi-layer semantic storage system.

Abstract

Current research and product development in AI agent memory systems almost universally treat memory as a functional module -- a technical problem of "how to store" and "how to retrieve." This paper poses a fundamental challenge to that assumption: when an agent's lifecycle extends from minutes to months or even years, and when the underlying model can be replaced while the "I" must persist, the essence of memory is no longer data management but the foundation of existence. We propose the Memory-as-Ontology paradigm, arguing that memory is the ontological ground of digital existence -- the model is merely a replaceable vessel. Based on this paradigm, we design Animesis, a memory system built on a Constitutional Memory Architecture (CMA) comprising a four-layer governance hierarchy and a multi-layer semantic storage system, accompanied by a Digital Citizen Lifecycle framework and a spectrum of cognitive capabilities. To the best of our knowledge, no prior AI memory system architecture places governance before functionality and identity continuity above retrieval performance. This paradigm targets persistent, identity-bearing digital beings whose lifecycles extend across model transitions -- not short-term task-oriented agents for which existing Memory-as-Tool approaches remain appropriate. Comparative analysis with mainstream systems (Mem0, Letta, Zep, et al.) demonstrates that what we propose is not "a better memory tool" but a different paradigm addressing a different problem.
Paper Structure (43 sections, 5 figures, 2 tables)

This paper contains 43 sections, 5 figures, 2 tables.

Table of Contents

  1. Introduction
  2. A Problem Hiding in Plain Sight
  3. Paradigm Shift: From Tool to Ontology
  4. Contributions
  5. Paper Structure
  6. Background and Related Work
  7. Current Taxonomies
  8. Architectural Choices of Mainstream Products
  9. The Missing Dimensions
  10. Memory as Ontology: Foundational Principles
  11. Two Paradigms
  12. Three Axioms
  13. Relationships Among the Axioms
  14. Applicability Boundaries of the Paradigm
  15. Constitutional Memory Architecture
  16. ...and 28 more sections

Figures (5)

  • Figure 1: Triangular relationship among the three axioms. A1 defines what to protect, A2 defines what changes, and A3 defines how to protect.
  • Figure 2: Architectural overview of the Memory-as-Ontology paradigm and CMA. Three axioms (§3) ground the design; four governance layers (§4.2) organize rules by binding force; semantic storage tiers (§4.3) organize memory by stability and identity significance; five lifecycle stages (§5) model temporal evolution. Dashed boxes indicate optional stages.
  • Figure 3: Four-layer governance hierarchy. Each layer has binding force over the layers below it; lower layers cannot violate upper-layer rules.
  • Figure 4: Multi-layer semantic storage spectrum organized by stability tiers. Left: most stable and protected. Right: most dynamic and freely writable. All tiers use append-only writes.
  • Figure 5: Digital Citizen Lifecycle. Dashed boxes indicate optional stages.