Portable Agent Memory: A Protocol for Cryptographically-Verified Memory Transfer Across Heterogeneous AI Agents
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914555252178944 |
|---|---|
| author | Ravindran, Santhosh Kumar |
| author_facet | Ravindran, Santhosh Kumar |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_11032 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Portable Agent Memory: A Protocol for Cryptographically-Verified Memory Transfer Across Heterogeneous AI Agents Ravindran, Santhosh Kumar Cryptography and Security Artificial Intelligence 68T42 I.2.11; I.2.6 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. |
| title | Portable Agent Memory: A Protocol for Cryptographically-Verified Memory Transfer Across Heterogeneous AI Agents |
| topic | Cryptography and Security Artificial Intelligence 68T42 I.2.11; I.2.6 |
| url | https://arxiv.org/abs/2605.11032 |