CyberIntel ⬡ News
★ Saved ◆ Cyber Reads
← Back ◬ AI & Machine Learning May 13, 2026

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

arXiv Security Archived May 13, 2026 ✓ Full text saved

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 w

Full text archived locally
✦ AI Summary · Claude Sonnet


    Computer Science > Cryptography and Security [Submitted on 10 May 2026] Portable Agent Memory: A Protocol for Cryptographically-Verified Memory Transfer Across Heterogeneous AI Agents Santhosh Kumar Ravindran 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. Comments: 8 pages, 28 references Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) MSC classes: 68T42 ACM classes: I.2.11; I.2.6 Cite as: arXiv:2605.11032 [cs.CR]   (or arXiv:2605.11032v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2605.11032 Focus to learn more Submission history From: Santhosh Kumar Ravindran [view email] [v1] Sun, 10 May 2026 23:24:06 UTC (18 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-05 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)
    💬 Team Notes
    Article Info
    Source
    arXiv Security
    Category
    ◬ AI & Machine Learning
    Published
    May 13, 2026
    Archived
    May 13, 2026
    Full Text
    ✓ Saved locally
    Open Original ↗