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.

翻译：代理记忆框架——mem0、Letta/MemGPT、Cognee、Zep/Graphiti、MemoryOS、MemTensor——各自推出了独立的SDK、存储布局和操作词汇表。目前缺乏统一的线格式：每次集成都是定制化的，每次迁移都需从头重建记忆，且没有框架提供治理界面让人类在写入长期存储前进行审核。我们提出memorywire——一种基于JSON-Schema 2020-12的线格式，支持对四种记忆类型（语义记忆、情景记忆、程序记忆、情感记忆）的五种操作（记忆、回忆、遗忘、合并、过期），并包含MemoryStore接口、扇出路由器和可选的HITL治理通道。我们描述了一个开源参考实现，包含五个后端适配器（sqlite-vec、mem0、Letta、Cognee、pgvector）；基于100个事实/50个查询的标注语料库（42个非空黄金ID+8个无匹配探针）的微基准测试表明，在42个黄金ID查询上Recall@5=1.000，摄入延迟P50=37.8毫秒，回忆延迟P50=40.6毫秒；对抗融合实验显示，在1对N等级0注入扫描（K∈{0，5，...，50}）中，互惠等级融合保持Recall@5=1.000，而最大融合在K≥5时下降至0.500，泄露率达80%；跨适配器16场景一致性测试通过80个单元中的68个，零失败。本贡献并非提出新算法，而是将成熟组件（RRF、FSM、STM/LTM巩固、差异与批准工作流）封装为一种与平台无关的协议，并附有经实证验证的参考实现，旨在与模型上下文协议协同而非竞争。