Unverified50% confidenceFactExact time
SurrealDB's multi-model capability unifies graph, vector and document capabilities in the same database, so that Agent Memory does not need to synchronize data across multiple systems.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
Unverified共享记忆在多智能体系统中通常通过向量数据库实现，将经验转化为高维向量嵌入存储于 Pinecone、Weaviate、Chroma 等向量数据库中，供其他智能体通过语义相似度检索调用72% similarVerifiedTechnical implementation paths for shared memory systems include structured storage in relational databases, semantic storage in vector databases, and a hybrid architecture combining graph databases with vector indexing.71% similarUnverifiedGraph databases store relationships as first-class citizens, enabling multi-hop relationship queries to be completed in milliseconds via graph traversal algorithms without the need to perform costly multi-table JOIN operations.71% similarUnverifiedOrientDB将文档模型、图模型与面向对象模型三者统一在同一存储引擎之上，是最早融合三者的多模型数据库之一70% similarUnverifiedDatabase-type projects such as Neon and Dolt host refs metadata in separate strongly consistent storage systems (such as etcd or PostgreSQL) while offloading large-volume packfile data to object storage, forming a hybrid architecture.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1030819API
curl https://kongchang.com/api/v1/knowledge/claims/1030819MCP
get_claim(id=1030819)