memorywire: A Vendor-Neutral Wire Format for Agent Memory Operations

• URL: http://arxiv.org/abs/2606.01138v2
• Date: Wed, 03 Jun 2026 07:59:47 GMT
• Title: memorywire: A Vendor-Neutral Wire Format for Agent Memory Operations
• Abstract summary: We present memorywire, a framework that lets a human review writes before they enter long-term storage.<n>We describe an open-source reference implementation with five backend components.<n>A 16-scenario cross-adapter conformance suite passes 68 of 80 cells with zero failures.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Agent-memory frameworks -- mem0, Letta/MemGPT, Cognee, Zep/Graphiti, MemoryOS, MemTensor -- each ship their own SDK, storage layout, and operational vocabulary. There is no shared wire format: every integration is bespoke, every migration rebuilds memory from scratch, and no framework ships a governance surface that lets a human review writes before they enter long-term storage. We present memorywire, a JSON-Schema 2020-12 wire format for five memory operations (remember, recall, forget, merge, expire) over four memory types (semantic, episodic, procedural, emotional), with a MemoryStore interface, a fan-out router, and an optional HITL governance channel. We describe an open-source reference implementation with five backend adapters (sqlite-vec, mem0, Letta, Cognee, pgvector); a microbenchmark on a 100-fact / 50-query labelled corpus (42 with non-empty gold ids + 8 no-match probes) achieving recall@5 = 1.000 on the 42 gold-id queries with ingest p50 = 37.8 ms and recall p50 = 40.6 ms; an adversarial-fusion experiment showing Reciprocal Rank Fusion holds recall@5 = 1.000 across a 1-of-N rank-0 injection sweep (K in {0, 5, ..., 50}) where max fusion collapses to 0.500 with 80% leak at K >= 5; and a 16-scenario cross-adapter conformance suite passing 68 of 80 cells with zero failures. The contribution is not a new algorithm; it is a packaging of established components (RRF, FSMs, STM/LTM consolidation, diff-and-approve workflows) into a venue-neutral protocol with an empirically validated reference, positioned to compose with the Model Context Protocol rather than compete with it.

Related papers

• Dual-Grained Agent Memory and Shapley Context Attribution for Multimodal Agentic Learner [55.80248281761638]
  multimodal large language models (MLLMs) deliver impressive perception yet still falter on scientific and mathematical reasoning.<n>We propose DG-Mem, a dual-grained agentic memory framework that augments a frozen MLLM with a non- externally stored memory built once from training-time rollouts and consulted read-only at test time.
  arXiv  Detail & Related papers  (2026-08-24T13:56:01Z)
• MemoryLake on MemoryArena: A Matched Study of Agent Memory Backends [8.130461324371604]
  We compare MemoryLake with Mem0, text-embedding-3-small vector RAG, and a long-context control across all five MemoryArena domains.<n>Because each backend bundles write, retrieval, consolidation, budgeting, and prompt-assembly choices, the study is a matched system-level comparison.
  arXiv  Detail & Related papers  (2026-08-14T02:19:26Z)
• Caching for the Future: Scrub Jay Episodic Memory Principles for Agent Memory Systems [5.321970297768025]
  Existing memory architectures treat all memories as equally persistent and systematically contaminate retrieved context with outdated facts.<n>We show that per-memory, type-conditioned temporal decay, can be operationalized as an auto-classified coefficient $_i$ in an external LLM-agent memory store.<n>We introduce the Temporal Generalization Test (TGT), a benchmark with held-out retention intervals and a Generalization Gap (GenGap) metric.
  arXiv  Detail & Related papers  (2026-08-05T12:12:44Z)
• Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents [72.3752981234916]
  Large Language Model (LLM) agents increasingly rely on external memory systems to accumulate experience across tasks.<n>We present Memory as a Controlled Process (MemCon), a framework that models memory operations as a Markov Decision Process.<n>MemCon consistently outperforms multiple memory baselines by up to 15.2 points in task success while reducing token consumption by 5-20%.
  arXiv  Detail & Related papers  (2026-07-15T08:32:40Z)
• FluctlightDB: A Memory Model of Data for AI Agents [1.3537117504260623]
  FluctlightDB is an embedded engine that implements this contract via experience() and activate.<n>On LoCoMo, CHORUS recalls 99.0% on an internally reproduced July 2026 run.
  arXiv  Detail & Related papers  (2026-07-10T09:18:32Z)
• When Claws Remember but Do Not Tell: Stealthy Memory Injection in Persistent Personal Agents [55.87577638514179]
  We study the threat as stealth memory injection, in which a remote black-box delivers a single email payload that must induce the agent to poisoned memory.<n>We propose MemGhost, a one-shot payload generation framework.<n>Across 56 held-out test cases, MemGhost achieves 87.5% end-to-end success on OpenClaw with GPT-5.4 and 71.4% on Claude Code SDK with Sonnet 4.6.
  arXiv  Detail & Related papers  (2026-07-06T15:08:58Z)
• Entity-Collision: A Stratified Protocol for Attributing Retrieval Lift in Agent Memory [0.0]
  End-to-end agent-memory benchmarks report a single hit@k per retriever.<n>We propose entity-collision, a system-agnostic protocol that pins the BM25 floor by construction.
  arXiv  Detail & Related papers  (2026-05-28T09:02:48Z)
• MemGym: a Long-Horizon Memory Environment for LLM Agents [69.79226770543049]
  We present MemGym, a benchmark for agentic memory that unifies existing agent gyms and in-house memory-grounded pipelines.<n>MemGym reports memory-isolated scores that decouple memory performance from reasoning, retrieval, and tool-use ability.<n>Our synthetic pipelines for MEMGYM-CODEQA and MEMGYM-DR are length-controllable, ablation-verified at every stage, and tightly aligned with downstream scenarios.
  arXiv  Detail & Related papers  (2026-05-20T07:25:33Z)
• CommitDistill: A Lightweight Knowledge-Centric Memory Layer for Software Repositories [0.5872014229110213]
  Software accumulate large amounts of unstructured knowledge in commit messages, pull-request discussions, and issue threads.<n>Recent work on typed-memory architectures for agents (MemGPT, generative agents, and the PlugMem module of Yang et al.) argues that agent memory should be distilled, typed knowledge rather than raw interaction text.<n>We adapt that stance to a software repository's own git history under a constrained regime: deterministic, dependency-free, local-only, no embeddings.
  arXiv  Detail & Related papers  (2026-05-18T12:14:28Z)
• MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGs [47.66730296440261]
  We introduce MemQ, which propagates credit backward through a provenance DAG that records which memories were retrieved when each new memory was created.<n>Across six benchmarks, MemQ achieves the highest success rate on all six in generalization evaluation and runtime learning.<n>We further study how $$ and $$ interact with the EC-MDP structure, providing principled guidance for parameter selection and future research.
  arXiv  Detail & Related papers  (2026-05-08T18:30:24Z)
• MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agents [20.000127976303606]
  We present Mem, a write-side memory router that decouples memory admission from the downstream answer backbone.<n>Mem predicts whether the turn should be stored using lightweight classification heads while training only 12M parameters.
  arXiv  Detail & Related papers  (2026-05-01T02:33:50Z)
• ZenBrain: A Neuroscience-Inspired 7-Layer Memory Architecture for Autonomous AI Systems [51.56484100374058]
  On LongMemEval-500, ZenBrain matches a long-context oracle's binary-judge accuracy to within 4.5 pp.<n> ZenBrain is a 7-layer neuroscience-inspired memory architecture.
  arXiv  Detail & Related papers  (2026-04-26T20:39:19Z)
• EngramaBench: Evaluating Long-Term Conversational Memory with Structured Graph Retrieval [0.0]
  EngramaBench is a benchmark for long-term conversational memory built around five personas, one hundred multi-session conversations, and one hundred fifty queries.<n>We evaluate Engrama, a graph-structured memory system, against GPT-4o full-context prompting and Mem0, an open-source vector-retrieval memory system.
  arXiv  Detail & Related papers  (2026-04-23T02:51:42Z)
• Memory Transfer Learning: How Memories are Transferred Across Domains in Coding Agents [56.078070829341534]
  Memory-based self-evolution has emerged as a promising paradigm for coding agents.<n>We investigate textbfMemory Transfer Learning (MTL) by harnessing a unified memory pool from heterogeneous domains.
  arXiv  Detail & Related papers  (2026-04-15T15:50:29Z)
• MemX: A Local-First Long-Term Memory System for AI Assistants [0.0]
  We present MemX, a local-first long-term memory system for AI with stability-oriented retrieval design.<n>MemX is implemented in Rust on top of lib and an OpenAI-compatible embedding API, providing persistent, searchable, and explainable memory for conversational agents.
  arXiv  Detail & Related papers  (2026-03-17T06:39:54Z)
• RMM: Reinforced Memory Management for Class-Incremental Learning [102.20140790771265]
  Class-Incremental Learning (CIL) trains classifiers under a strict memory budget. Existing methods use a static and ad hoc strategy for memory allocation, which is often sub-optimal. We propose a dynamic memory management strategy that is optimized for the incremental phases and different object classes.
  arXiv  Detail & Related papers  (2023-01-14T00:07:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.