Portable Agent Memory: A Protocol for Cryptographically-Verified Memory Transfer Across Heterogeneous AI Agents

TL;DR

This paper introduces Portable Agent Memory, an open protocol for securely transferring rich, structured memory states across diverse AI agents, enhancing interoperability and tamper-evidence.

Contribution

It presents a novel structured memory model, a secure transfer protocol, and a practical SDK enabling cross-model memory sharing among leading AI architectures.

Findings

Successful cross-model memory transfer between GPT-4, Claude, Gemini, and Llama.

The protocol ensures tamper-evidence and selective disclosure of memory segments.

Open-source implementation with extensive testing demonstrates practical viability.

Abstract

We present Portable Agent Memory, an open protocol and reference implementation for transferring persistent memory state across heterogeneous AI agents. Modern AI agents accumulate rich context -- episodic events,semantic knowledge, procedural skills, working state, and identity preferences -- but this context remains locked within vendor-specific runtimes. Portable Agent Memory addresses this through: (1) a five-component structured memory model with content-addressable entries linked by a Merkle-DAG provenance graph providing tamper-evidence; (2) capability-based access control enabling selective, scoped disclosure of memory segments; (3) an injection-resistant rehydration protocol that adapts recalled content to heterogeneous target models while mitigating indirect prompt injection; and (4) a JSON-first serialization format with optional CBOR compaction for efficient transport. We provide a Python SDK with 54 passing tests, agent skills for multiple platforms, and demonstrate cross-model memory transfer between GPT-4, Claude, Gemini, and Llama architectures. The protocol is open-source under Apache 2.0.