Unverified50% confidenceFactTime unknown
Hermes Agent's memory system uses a 'file-as-memory' approach rather than RAG (Retrieval-Augmented Generation) with vector databases.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026
Sources
Related Claims
UnverifiedHermes是一个开源成长型助理，实现记忆沉淀依赖向量数据库（如Chroma、Weaviate）和结构化工作流两类核心机制70% similarUnverifiedHermes的记忆系统包含Memory.md和User.md基础层、SQLite加FTS5全文检索的Session数据库，以及8个可选的外部Memory Provider70% similarPartially VerifiedHermes Agent使用向量数据库（如ChromaDB或Qdrant）将对话历史和知识片段转换为高维向量进行存储和语义检索69% similarUnverifiedThe Long-term Memory layer in Hermes can be persisted to vector databases such as Pinecone and Weaviate, with retrieval via semantic search69% similarUnverifiedThe Material Mining Agent uses a RAG (Retrieval-Augmented Generation) architecture that vectorizes user-input documents and stores them in a vector database68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/56118API
curl https://kongchang.com/api/v1/knowledge/claims/56118MCP
get_claim(id=56118)