EPS
← All batches·2605.11032

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

topic: general_aitop score: 100released: 2026-05-13first surfaced: 2026-05-13arXivPDFlinked_to_results2026-05-13

Authors: Santhosh Kumar Ravindran

arXiv · PDF

Summary

The authors propose Portable Agent Memory, an open protocol for transferring an AI agent's accumulated context (episodic events, knowledge, skills, working state, identity preferences) across different vendor platforms and model architectures. The protocol uses a five-part structured memory model with content-addressable entries linked by a Merkle-DAG for tamper-evidence, capability-based access control for selective disclosure, and an injection-resistant rehydration protocol that adapts recalled memory to heterogeneous target models. They provide a Python SDK with 54 tests and demonstrate cross-model memory transfer between GPT-4, Claude, Gemini, and Llama.

Main takeaways:

  • AI agents accumulate rich context, but it's locked in vendor-specific runtimes; this protocol makes memory portable across heterogeneous models and platforms.
  • Memory is structured as five components (episodic, semantic, procedural, working, identity) with content-addressable entries linked by a Merkle-DAG for tamper-evidence and provenance.
  • Capability-based access control lets agents selectively share memory segments; the rehydration protocol adapts recalled content to target models while mitigating indirect prompt injection.
  • Demonstrated working cross-model transfers between GPT-4, Claude, Gemini, and Llama with a Python SDK and agent skills for multiple platforms.
  • Open-source under Apache 2.0 with a JSON-first serialization format and optional CBOR compaction.

Relevance

Tangentially relevant: if I'm investigating how personas or behaviors are installed and transferred (prompt vs. fine-tuning vs. steering), this protocol's approach to serializing and rehydrating agent state across models could inform how I think about representing and migrating persona-defining context. The injection-resistant rehydration is also adjacent to my interest in how behaviors condition on context.

Abstract

arXiv:2605.11032v1 Announce Type: new 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.