CRAIDCMay 31

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

arXiv:2606.0113847.6Has Code
AI Analysis

For developers integrating agent memory frameworks, this work provides a standardized protocol to reduce bespoke integration effort and enable governance, though it is an incremental packaging of existing techniques.

The paper introduces memorywire, a vendor-neutral wire format for agent memory operations, achieving recall@5 = 1.000 on a labelled corpus with ingest p50 = 37.8 ms and recall p50 = 40.6 ms, and demonstrating robustness in adversarial fusion experiments.

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 achieving recall@5 = 1.000 on the 42 labelled 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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes