wly8691-jpg/knowlp-rag

Name: wly8691-jpg/knowlp-rag
Author: wly8691-jpg

Plugin插件 Native原生 ⭐ 2 MIT Memory & Knowledge记忆与知识库 Docs & Writing文档与写作

KnowLP-RAG：用于Markdown笔记的双知识图谱RAG — dsh插件添加 @eqman00003/knowlp-rag · 为DeepSeek Harness (dsh)与Claude Code提供的MCP及原生Cordis插件

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

KnowLP-RAG is an agent-first knowledge retrieval tool that turns your Markdown notes into a self-maintaining, use-it-or-lose-it knowledge graph. It supports multiple AI agents including DeepSeek Harness (DSH) and Claude Code, and only requires human input for the vault path where notes are stored. To install the plugin in DSH, you simply run the command dsh plugin add "@eqman00003/knowlp-rag" from the command line, then set two required environment variables for your vault and index directory. Unlike basic vector search, it prioritizes notes you should actually read for your query, not just documents that contain matching keywords.

KnowLP-RAG ships with six tools to cover the full lifecycle of knowledge retrieval and graph maintenance. The knowlp_search tool runs four-engine fan-out retrieval, knowlp_get_note safely pulls note content without path traversal risks, knowlp_stats checks engine and graph health for troubleshooting, and the remaining tools let you record explicit feedback and preference pairs to improve the graph over time. All setup steps after providing the vault path are handled automatically by the agent, so you don’t need to manually run build or check commands. It is ideal for users who keep Markdown notes and want to add a second-brain capability to their AI agent, and it works out of the box with Chinese note vaults.

KnowLP-RAG requires Python 3.11 or newer to run, and it is released under the open source MIT license. It includes an optional PixelRAG visual retrieval engine that offloads visual embedding work to a separate GPU machine on your network, accessible via a network path like Tailscale. If you do not configure PixelRAG, the plugin falls back to n-gram and embedding retrieval modes that work without a dedicated GPU. When you run your first search after installation, the plugin will automatically bootstrap the Python environment, a process that takes around 30 seconds, so you should not interrupt it until it completes.

这是一个面向智能体的知识检索插件，核心能力是将用户的Markdown笔记转化为可自维护的知识图谱，实现"用进废退"式的动态知识管理。它支持双图检索引擎，同时集成了向量、全文检索能力，最终返回带阅读顺序、依赖链和相似替代笔记的检索结果，目前同时支持DeepSeek Harness（DSH）和Claude Code两类智能体。

用户仅需提供本地笔记库的路径，其余安装、构建图谱、健康自检步骤均可由智能体自动完成。插件提供六大工具，涵盖检索、获取笔记内容、引擎健康自检、记录用户反馈和偏好修正，满足知识检索和动态调优的全流程需求。它适合使用Markdown记笔记、需要为智能体添加第二大脑能力的用户，原生适配中文笔记库。

本插件基于Python开发，要求Python 3.11及以上版本，采用MIT许可证完全开源。可选的PixelRAG视觉检索模块需要额外配置网络可访问的独立GPU机器，未配置该功能时不影响基础文本检索功能正常使用。首次运行检索时会自动完成Python环境引导安装，过程大约需要30秒，提示完成前请勿中断操作。

View on GitHub在 GitHub 查看

Send to your DSH发给你的 DSH 安装

请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】，检查通过再动手。

插件：knowlp-rag（wly8691-jpg/knowlp-rag）
仓库：https://github.com/wly8691-jpg/knowlp-rag
本站详情页：https://www.yhbd.top/plugins/wly8691-jpg-knowlp-rag/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 2 · 最近提交 2026-09-07 · 主语言 Python

按下面顺序执行，每步先把结论告诉我，再进入下一步：

【1 兼容性检查】
① 我这边：DSH 版本、Node 版本、操作系统、当前 profile（web / desktop）。
② 读它的 README、package.json、插件 manifest，列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对，结论只写「满足 / 不满足 / 未知」三种；不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突：命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。

【2 安全性检查】
① 仓库可信度：和上面「本站登记」是否一致；star / fork 数、创建时间、最近提交，是否归档或长期停更。
② 安装脚本：逐行看 package.json 的 preinstall / install / postinstall，以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名，立刻停下来告诉我，不要继续装。
③ 依赖：列出新增依赖，标出无人维护、或与知名包拼写近似的可疑包（typosquatting）。
④ 权限与副作用：它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限（filesystem / network / shell / clipboard 等），以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限，或权限明显超出功能所需，先停下来问我。

【3 安装】
上面两步没有「不满足」和「高危项」时才执行；用官方推荐方式安装，不要自行提权。

【4 汇报】
用表格输出：检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜，也不要替我决定。

Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH：它会先核对兼容性与安全性（逐条给「满足 / 不满足 / 未知」），确认没问题再安装，有高危项会停下来问你。框内可滚动，复制到的是完整提示词；安装命令不一定准确，发给 DSH 更稳。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意

Only 2 stars - very few users, little community feedback星标只有 2，几乎没人在用，遇到问题缺少社区反馈

DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时（Electron / Python / Docker 等）是否齐备
Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突：命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致，是否归档或长期停更
Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需（filesystem / network / shell / clipboard）
Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限，以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照，不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装（适合开发者）

CLI Install命令行安装

dsh plugin add "@eqman00003/knowlp-rag"

把 wly8691-jpg/knowlp-rag 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

5.6 KB · 缓存于 2026-10-01 22:13:32 · 5.6 KB

type: KnowLP文档文档状态: 引擎日期: "2026-08-29" 说明: 引擎 README（v3.0.8 仓库版，dsh 优先）

KnowLP-RAG

Agent-first knowledge retrieval — turn your Markdown notes into a self-maintaining knowledge graph that is "use it or lose it". Agents (DSH / Claude Code) install, build the graph, and self-check it; only the vault path must be provided by the human. Retrieval returns reading paths: which notes to read, in what order, and which are similar substitutes.

Quick start (3 steps)

All three steps are agent-runnable; only KNOWLP_VAULT (your notes directory) must be provided by the human.

# 1. Install (official npm registry)
dsh plugin add "@eqman00003/knowlp-rag"

# 2. Set the two required env vars (without them the dual-graph engine idles and only full-text search works)
export KNOWLP_VAULT="$HOME/Notes"              # your Markdown notes directory
export KNOWLP_GRAPH_DIR="$HOME/.knowlp-dsh"    # writable index directory

# 3. Restart dsh web — the first search triggers Python env bootstrap (~30s, don't interrupt)

Try the demo vault (no private data, no embedding model)

A 7-note bilingual demo vault ships with the repo. From clone to first search:

POSIX:

pip install -e .
export KNOWLP_VAULT="$PWD/examples/demo-vault"
export KNOWLP_GRAPH_DIR="$PWD/.demo-graph"
python build_graph.py && python -m vector_index --build
python knowlp_search.py "How should I understand this RAG architecture?" --hybrid

Windows PowerShell:

pip install -e .
$env:KNOWLP_VAULT = "$PWD\examples\demo-vault"
$env:KNOWLP_GRAPH_DIR = "$PWD\.demo-graph"
python build_graph.py; python -m vector_index --build
python knowlp_search.py "How should I understand this RAG architecture?" --hybrid

Five bilingual verification queries and what each demonstrates: docs/demo.md. Agent onboarding instructions: examples/agent-setup.md.

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要，完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

渲染基于仓库 wly8691-jpg/knowlp-rag 的 README.md。在 GitHub 查看原文 →