# Memory as Metabolism: A Design for Companion Knowledge Systems

arXiv: https://arxiv.org/abs/2604.12034 · HTML: https://mlsanity.com/paper/2604.12034/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation.
- Builds on 28 of its 49 references that are in the map.
- First posted on arXiv 13 Apr 2026.

## Placed in

- Retrieval-augmented generation / [Agentic RAG, agents and memory](https://mlsanity.com/rag/agentic-rag-agents-and-memory/)

## Builds on (most cited first, 28 of 28)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://mlsanity.com/paper/2208.03299/) (2022)
- [Towards Federated Learning at Scale: System Design](https://mlsanity.com/paper/1902.01046/) (2019)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [MemoryBank: Enhancing Large Language Models with Long-Term Memory](https://mlsanity.com/paper/2305.10250/) (2023)
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [ShortGPT: Layers in Large Language Models are More Redundant Than You Expect](https://mlsanity.com/paper/2403.03853/) (2024)
- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025)
- [DeepSeek-OCR: Contexts Optical Compression](https://mlsanity.com/paper/2510.18234/) (2025)
- [LightMem: Lightweight and Efficient Memory-Augmented Generation](https://mlsanity.com/paper/2510.18866/) (2025)
- [MemOS: A Memory OS for AI System](https://mlsanity.com/paper/2507.03724/) (2025)
- [From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs](https://mlsanity.com/paper/2504.15965/) (2025)
- [Towards Lifelong Dialogue Agents via Timeline-based Memory Management](https://mlsanity.com/paper/2406.10996/) (2024)
- [Context Cascade Compression: Exploring the Upper Limits of Text Compression](https://mlsanity.com/paper/2511.15244/) (2025)
- [MemMachine: A Ground-Truth-Preserving Memory System for Personalized AI Agents](https://mlsanity.com/paper/2604.04853/) (2026)
- [AI-native Memory 2.0: Second Me](https://mlsanity.com/paper/2503.08102/) (2025)
- [The AI Hippocampus: How Far are We From Human Memory?](https://mlsanity.com/paper/2601.09113/) (2026)
- [Learning to Forget: Sleep-Inspired Memory Consolidation for Resolving Proactive Interference in Large Language Models](https://mlsanity.com/paper/2603.14517/) (2026)
- [To Mask or to Mirror: Human-AI Alignment in Collective Reasoning](https://mlsanity.com/paper/2510.01924/) (2025)
- [D-Mem: A Dual-Process Memory System for LLM Agents](https://mlsanity.com/paper/2603.18631/) (2026)
- [The network structure of scientific revolutions](https://mlsanity.com/paper/2010.08381/) (2020)
- [Optical Context Compression Is Just (Bad) Autoencoding](https://mlsanity.com/paper/2512.03643/) (2025)
- [Context Cartography: Toward Structured Governance of Contextual Space in Large Language Model Systems](https://mlsanity.com/paper/2603.20578/) (2026)

## Built on by (most cited first, 1 of 1)

- [Mi-Memory: A Lifecycle Memory Framework for Personal AI](https://mlsanity.com/paper/2607.18975/) (2026)

## Abstract (arXiv)

Retrieval-Augmented Generation remains the dominant pattern for giving LLMs persistent memory, but a visible cluster of personal wiki-style memory architectures emerged in April 2026 -- design proposals from Karpathy, MemPalace, and LLM Wiki v2 that compile knowledge into an interlinked artifact for long-term use by a single user. They sit alongside production memory systems that the major labs have shipped for over a year, and an active academic lineage including MemGPT, Generative Agents, Mem0, Zep, A-Mem, MemMachine, SleepGate, and Second Me. Within a 2026 landscape of emerging governance frameworks for agent context and memory -- including Context Cartography and MemOS -- this paper proposes a companion-specific governance profile: a set of normative obligations, a time-structured procedural rule, and testable conformance invariants for the specific failure mode of entrenchment under user-coupled drift in single-user knowledge wikis built on the LLM wiki pattern. The design principle is that personal LLM memory is a companion system: its job is to mirror the user on operational dimensions (working vocabulary, load-bearing structure, continuity of context) and compensate on epistemic failure modes (entrenchment, suppression of contradicting evidence, Kuhnian ossification). Five operations implement this split -- TRIAGE, DECAY, CONTEXTUALIZE, CONSOLIDATE, AUDIT -- supported by memory gravity and minority-hypothesis retention. The sharpest prediction: accumulated contradictory evidence should have a structural path to updating a centrality-protected dominant interpretation through multi-cycle buffer pressure accumulation, a failure mode no existing benchmark captures. The safety story at the single-agent level is partial, and the paper is explicit about what it does and does not solve.