Bryan-cmf/dsh-vector-memory

README 摘要

🧠 Vector Memory — DSH-Plugin 可持久化的 Agent 記憶核心 —— mem save / mem search / mem health ,跨 session、跨重啟,零外部依賴。 A DeepSeek Harness plugin that gives your agents durable, cross-session memory — the same mem save / mem search contract as the original Bryan-cmf/vector-memory MCP server, but natively on DSH. Why a native rewrite (and what changed) The 2026 memory landscape made self-hosting a Qdrant + BGE-m3 stack a commodity (Zep / Mem0 / Letta / LangMem all offer managed embeddings + graph memory). This package keeps the agent-facing contract and drops the infrastructure : Aspect Old (MCP server) This plugin Storage Qdrant (Docker) + BGE-m3 ( 2GB) DSH storageDomain — durable JSON backend, zero setup Retrieval Vector similarity v1: deterministic keyword scoring + recency; embeddings pluggable in v2 Interface MCP stdio (Claude/Cursor/…) Native tools ( mem save / mem search / mem health ) + vectorMemory service Persistence Manual install script Bundle row — it just works Tools Tool Effect mem save { content, tags?, ttlDays? } → durable memory, returns id mem search { query, limit? } → ranked hits (score, content, tags, created) mem health record count, expired count, domain status, TTL polic…

分类