DSH Plugin Directory

Memory

dsh-vector-memory

Bryan-cmf/dsh-vector-memory · ★ 0

Bryan-cmf

DSH-Plugin: durable agent memory core - mem_save/mem_search/mem_health backed by storageDomain (survives restarts), 記憶 view tab.

RepositorySource
License
MIT
Added
2026-08-17
Maintenance
active
Install kind
github
Manifest details
Manifest status
Declared
Manifest path
package.json#dsh
Manifest checked
2026-08-19
Lifecycle scripts
None found

Static manifest checks report declarations only; they are not compatibility or security review.

安装

dsh plugin --profile web add github:Bryan-cmf/dsh-vector-memory

GitHub 源码安装：首次需按提示配置 allowBuilds 构建授权后重试

For install and environment setup, plus plugin development tutorials, see DSH community docs ↗

README

Source README · body: en · Read Chinese README

Table of contents
  1. 🧠 Vector Memory — DSH-Plugin
  2. Why a native rewrite (and what changed)
  3. Tools
  4. Dashboard
  5. Install
  6. Requirements
  7. Configuration
  8. Roadmap
  9. Development
  10. License

⚠️ 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

Memory

hindsight#coding-agents

vectorize-io

vectorize-io/hindsight/hindsight-integrations/coding-agents

Hindsight：会学习的 Agent 长期记忆系统，自动召回/保存、知识页、深度反思与按仓库隔离的记忆银行。

View detailsdsh plugin --profile web add github:vectorize-io/hindsight#path:/hindsight-integrations/coding-agents
☆ 61,084github
Memory

dsh-memory-plugin

volcengine

volcengine/OpenViking/examples/dsh-memory-plugin

面向 DeepSeek Harness 的 OpenViking 记忆与上下文插件：pre-step 自动召回与画像注入、会话捕获、`viking://` URI 防护，以及对接 OpenViking 服务端的 recall/write 记忆工具。

View detailsdsh plugin --profile web add @openviking/dsh-memory-plugin
☆ 42,241npm
Memory

memos

memtensor

memtensor/memos

给你的 Agent 持久记忆与成长能力

View detailsdsh plugin --profile web add @memtensor/memos-cloud-dsh-plugin@latest
☆ 12,402npm
Memory

dsh-purge-kingchar

kingcharleslzy-ai

kingcharleslzy-ai/dsh-purge

让 AI 更专注地辅助学习与动手实验：DSH 附加组件，提供状态自检、提示词与规则管理、本机备份与回滚。

View detailsdsh plugin --profile web add 'github:kingcharleslzy-ai/dsh-purge#27919a326b6615b1968661a3e749760cec3a2e07'
☆ 8,375github
MemoryCurated

dsh-context

bowenliang123

bowenliang123/dsh-context

上下文洞察面板：一眼看清模型上下文窗口的组成与变化——构成对照窗口大小、按请求历史趋势、压缩/注入事件、消息级 token 统计。

View detailsdsh plugin --profile web add dsh-context
☆ 5,107npm
Memory

memsearch

zilliztech

zilliztech/memsearch/plugins/dsh

MemSearch plugin for DeepSeek Harness: shared markdown memory across agents, with capture, on-demand recall, memory-recall skill, and a skill-candidate review panel.

View detailsdsh plugin --profile web add '@zilliz/memsearch-dsh@0.1.8'
☆ 2,879npm