Local knowledge base for DSH: one Markdown file per note, with tags, hierarchical folders, full-text search, attachment opening via the system default app, zero-dependency Office text extraction, and citation into the conversation. Built for host DSH 0.2.0-rc.2; on Windows the default root is E:/dsh-kb.
Install
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:fangqiing/dsh-knowledge-lite
Any plugin you install runs third-party code with your own permissions — it can read your files, use your credentials, and reach the network, and tool approvals don’t sandbox it. GitHub-sourced plugins also run build scripts at install time — pnpm blocks those until you allow them, so an install can stop with ERR_PNPM_GIT_DEP_PREPARE_NOT_ALLOWED or ERR_PNPM_IGNORED_BUILDS; dsh prints the exact key to add under allowBuilds in your profile’s pnpm-workspace.yaml, and the install works on the next run. Allowing a build is a trust decision: only install sources you trust, and pin a commit (github:owner/repo#sha).
README
This plugin publishes its README in Chinese only.
给 DeepSeek Harness（dsh）用的本地知识库插件。每篇笔记是一个 Markdown 文件，数据完全在你本机，不依赖任何云服务。
功能
- 本地纯文本存储：每篇一个
.md，可用任意外部编辑器直接修改 - 全文搜索 + 标签筛选
- 层级目录：目录即磁盘文件夹，可在文件管理器里手动移动文件，库自动识别
- 附件：拖入文件自动分流
- 文本类（
.txt/.md/.py/.json/.csv…）→ 直接进正文 - Office（
.docx/.xlsx/.pptx）→ 原件存入files/，同时零依赖抽取文本写进正文（可搜索、可被 AI 引用） - 其他（
.pdf/图片/压缩包…）→ 原样存入files/，双击「打开」交给系统程序 - 删除笔记连带清理其附件
- 文本类（
- 拖拽移动：把笔记拖到任意目录节点即移动
- 对话导出：把 dsh 对话整理成笔记（writeback）——仅当该轮对话带文档/附件时才出现「存入知识库」按钮，纯文字回答不触发回写
安装
上架 DSH 插件市场后，可在 dsh 的 设置 → 插件市场 搜索 dsh-knowledge-lite 一键安装。
手动 / 开发模式（针对 dsh 0.2.0-rc.2 / Windows）：
git clone https://github.com/fangqiing/dsh-knowledge-lite.git
cd dsh-knowledge-lite
pnpm install # 依赖用 link: 协议，改动即时生效，无需重装
# 把插件链接进 dsh 的插件目录并重启 dsh（安装前需彻底退出 dsh，否则 EPERM）
宿主版本需与
peerDependencies中的@deepseek-ai/dsh-*0.2.0-rc.2匹配。
兼容性
- 宿主：DeepSeek Harness
0.2.0-rc.2 - 平台：Windows（默认笔记根目录写死
E:/dsh-kb，其他平台需改lib/config.js的DEFAULT_ROOT） - 分类建议：知识管理 / 效率工具
目录结构
| 文件 | 职责 |
|---|---|
lib/store.js |
笔记与层级目录的存储、扫描、移动、删除 |
lib/index.js |
宿主（Node）侧入口与 RPC |
lib/client.js |
浏览器半侧 UI（目录树、编辑器、附件列表） |
lib/attachments.js |
Office 文档零依赖文本抽取（ZIP + XML，无第三方库） |
lib/writeback.js |
把对话抽取为笔记候选 |
lib/config.js |
笔记根目录等路径配置 |
lib/writeback-prompts.js |
抽取提示词 |
已知限制
- 默认笔记根目录写死为
E:/dsh-kb（Windows 专属）。其他平台需改lib/config.js的DEFAULT_ROOT，或首次启动后在设置里改。 - 主要在 Windows + dsh
0.2.0-rc.2下验证。
License
MIT
Links
More in this category
vectorize-io/hindsight#coding-agents★ 52424
Hindsight, agent memory that learns: long-term project memory with auto recall and retain, knowledge pages, deep reflection, and per-repo memory banks.
volcengine/OpenViking#examples/dsh-memory-plugin★ 40541
OpenViking memory and context bundle for DeepSeek Harness: pre-step auto-recall and profile injection, session capture, `viking://` URI guarding, and recall/write memory tools backed by an OpenViking server.
agentscope-ai/ReMe#dsh★ 3667
Connects DeepSeek Harness to ReMe's local-first, self-evolving personal knowledge base: automatically captures completed main-agent conversations as user-owned Markdown memory, searches conversations and source material through reme_search with BM25, optional embeddings, and wikilink expansion, and schedules daily memory consolidation.
zilliztech/memsearch#MemSearch★ 2770
Shared Markdown memory for DSH and other coding agents, with automatic capture, pre-step context injection, searchable recall, and memory-to-skill self-evolution through a review panel.
vshulcz/deja-vu#extensions/dsh★ 1275
Reads the session files thirty-three other coding agents on this machine already wrote — Claude Code, Codex, Cursor, VS Code Copilot Chat, opencode, OpenClaw, Hermes, Kimi, Cline, Zed and more — including sessions from before it was installed: six tools (deja_recall, deja_session, deja_blame, deja_fix, deja_how, deja_remember), a /deja command, and optional automatic recall added to the runtime context. Local BM25 index, no LLM, no embeddings, no network (dsh plugin --profile web add dsh-deja).
adoresever/graph-memory★ 658
Traceable, searchable cross-session memory for DeepSeek Harness — conversation knowledge as typed graph nodes (TASK/SKILL/EVENT) and typed edges.
Community comments
Comments are public GitHub Discussions. Loading them connects to GitHub and Giscus; a GitHub account is required to post.