dsh-vector-memory
其他 活跃维护

dsh-vector-memory

Bryan-cmf/dsh-vector-memory

存储域实现智能体持久化向量记忆能力,支持记忆保存、检索与健康检查,服务重启后记忆数据不丢失,自带记忆可视化查看标签页,可快速集成到各类智能体开发系统中。

0
Stars 标星
0
Forks 分支
0
Watchers 关注
0
Open Issues
TypeScript
主要语言
MIT
开源协议
23 KB
仓库大小
1 个月前
最后推送
一键安装扩展 / 插件指令
dsh plugin --profile web add github:Bryan-cmf/dsh-vector-memory
git clone https://github.com/Bryan-cmf/dsh-vector-memory.git
git clone git@github.com:Bryan-cmf/dsh-vector-memory.git
README.md main

⚠️ 此套件已併入 @bryan-cmf/dsh-insights(2026-08-17)。此 repo 僅保留作合併前歷史,後續迭代請到 dsh-insights。

🧠 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。

npm
License: MIT
DSH

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 policy

Other plugins can inject: ['vectorMemory'] and call save / search /
health directly.

Dashboard

The client half registers a 「記憶」view tab (order 30, right of
chat / 軌跡 / 觀測) listing this session's saved/searched items live.

Install

"dsh": { "profile": { "bundles": ["@bryan-cmf/dsh-vector-memory"] } }

⚠️ This row publishes the vectorMemory service — it must live in the
host composition (process-global). If you mount it from an agent preset
instead, wrap it in a group with an isolate realm (see the DSH
composition docs).

Requirements

  • DSH >= 0.1.0-rc.6 — services: tools, storageDomain (domain layer +
    a storage backend, e.g. dsh-storage-json, are part of the shipped
    dsh-base bundle)

Configuration

Key Default Meaning
ttlDays 90 Default memory TTL; 0 = forever
maxResults 10 Default mem_search result count

Roadmap

  • v2: pluggable embedding backends (hosted embedders or Qdrant REST)
  • v2: MCP stdio dual-exit so the same store serves Claude Desktop / Cursor
  • v2: memory curation (merge/dedupe/forget jobs)

Development

pnpm install --store-dir .pnpm-store
pnpm build

License

MIT