让AI Agent的记忆跨平台安全迁移，防止篡改和泄露。
Portable Agent Memory: A Protocol for Cryptographically-Verified Memory Transfer Across Heterogeneous AI Agents
- 用结构化记忆+梅尔克树图追踪记忆来源，防篡改。
- 支持不同AI模型间记忆无缝转移，实测兼容GPT-4等四类模型。
- 可控制部分记忆共享，适合多平台协作场景。
我们提出Portable Agent Memory，一种开放协议与参考实现，用于在异构AI Agent间传递持久化记忆状态。现代AI Agent积累丰富上下文——事件经历、语义知识、程序技能、工作状态和身份偏好——但这些上下文被锁定在厂商特定运行时中。该协议通过：(1) 五组件结构化记忆模型，内容可寻址条目通过梅尔克-DAG溯源图提供篡改证据；(2) 基于能力的访问控制，实现记忆片段的选择性、范围化披露；(3) 抗注入的重激活协议，将召回内容适配异构目标模型，同时缓解间接提示注入风险；(4) 以JSON为主、可选CBOR压缩的序列化格式，提升传输效率。我们提供包含54个通过测试的Python SDK、多平台代理技能，并实证演示了GPT-4、Claude、Gemini与Llama架构间的跨模型记忆迁移。协议开源，采用Apache 2.0许可。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。