Luke-Yong/dsh-plugin-knowledge-graph
dsh-plugin-knowledge-graph 适用于 Deepseek Harness
Project Overview项目介绍
This is a native plugin built exclusively for DeepSeek Harness (DSH) that adds a read_graph tool backed by a codebase knowledge graph. The plugin tracks files, directories, and exported symbols along with their relationships, allowing the DSH agent to answer structural and dependency questions much faster than traditional grepping or reading full files. It currently supports parsing symbols from TypeScript, JavaScript, and Python codebases. To install the plugin, users can run the DSH CLI command dsh plugin --profile web add github:Luke-Yong/dsh-plugin-knowledge-graph, and pin to a specific commit hash by adding #<commit-sha> to the end of the repository URL for reproducible environments.
After installation, the plugin registers the read_graph tool that accepts two parameters: a required query string in the format <query_type> <target> and an optional workspace root that defaults to the current working directory. Users can run six types of queries: structure to get the full directory tree, exports, imports_of, exporters_of, dependents, and unused_imports. The knowledge graph model uses three node types (dir, file, symbol) and four edge types to represent all relationships between code components. This tool is ideal for DSH users who need to quickly understand unfamiliar codebases or debug dependency issues.
This project is currently in its infancy, so execution behavior, query interface, and compatibility may change as the community iterates on development and testing. If you want to build the plugin from source, you need to run npm run build to compile the TypeScript code, which outputs the built files to the dist directory with dist/index.js as the entry point. A key tip for first-time users is to always pass an explicit workspace root to avoid the default root including multiple unrelated projects, which can cause the structure query to return irrelevant data. The plugin is released under the open source MIT license, so it is free to use, modify, and distribute.
这是一个专为DeepSeek Harness(DSH)开发的原生插件,提供基于代码库知识图谱的read_graph查询工具。知识图谱会追踪代码仓库内每个文件、目录、导出符号及其关联关系,帮助AI代理更快回答代码结构和依赖相关问题,效率高于传统的文本搜索和逐文件读取方式,当前支持解析TypeScript/JavaScript和Python代码的符号信息。
用户可通过DSH命令行工具将该插件安装到个人配置文件中,也可固定到特定提交版本保证环境可复现。安装后插件会自动在DSH中注册read_graph工具,支持多种查询类型,包括输出完整目录树、列出文件导出符号、查询符号来源文件、查找依赖文件、列出未使用导入等。该插件面向需要梳理代码结构、分析依赖关系的DSH用户,帮助加速代码理解和开发流程。
该项目目前处于早期开发阶段,功能实现、查询接口和兼容性可能会随社区迭代测试发生变化。构建插件需要先执行npm run build命令编译TypeScript代码到dist目录,使用read_graph工具时建议明确传入工作区根路径,避免默认路径包含多个无关项目导致查询错误。项目采用MIT许可证开源,可免费使用和修改。
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:dsh-plugin-knowledge-graph(Luke-Yong/dsh-plugin-knowledge-graph)
仓库:https://github.com/Luke-Yong/dsh-plugin-knowledge-graph
本站详情页:https://www.yhbd.top/plugins/luke-yong-dsh-plugin-knowledge-graph/
本站登记:类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 4 · 最近提交 2026-08-17 · 主语言 TypeScript
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。
- Only 4 stars - very few users, little community feedback星标只有 4,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 --profile web add github:Luke-Yong/dsh-plugin-knowledge-graph
把 Luke-Yong/dsh-plugin-knowledge-graph 加入你的 DSH 配置(web profile)即可启用。
READMEREADME
dsh-plugin-knowledge-graph
A DeepSeek Harness (DSH) plugin that exposes a read_graph tool backed by a codebase knowledge graph. The graph tracks every file, directory, exported symbol, and their relationships so an agent can answer structural and dependency questions faster than grepping or reading files.
Status: infancy. This project is in its infancy stage. Execution behavior, the query surface, and compatibility may change while the project is iterated on and tested by the open source community.
Derived work. This project is derived from the knowledge graph tool in Luke-Yong/H, adapted to DeepSeek Harness's "everything is a plugin" model.
What it does
Given a workspace root, the plugin builds an in-memory graph and answers queries such as:
structure— print the full directory treeexports <file>— list every symbol exported by a fileimports_of <file>— list symbols a file imports (with their source files; stdlib/third-party imports are tagged)exporters_of <symbol>— find which files export a symboldependents <file>— find which files import from a fileunused_imports <file>— list imports never referenced in the file
Symbols are parsed from TypeScript/JavaScript (via the TypeScript compiler API) and Python (module-level def, class, and name = value bindings).
Graph model
The graph uses three node types and four edge types:
| Nodes | Meaning |
|---|---|
dir |
A directory |
file |
A source file |
symbol |
An exported symbol (function, class, const, type, interface, enum, default) |
| Edges | Meaning |
|---|---|
CONTAINS |
Structural parent → child (dir → dir/file, file → symbol) |
EXPORTS |
File → symbol it exports |
IMPORTS |
File-level dependency (file → file) |
IMPORTS_SYMBOL |
Precise symbol-level dependency (file → symbol) |
Installation
Install with the DSH CLI into a profile:
dsh plugin --profile web add github:Luke-Yong/dsh-plugin-knowledge-graph
Pin to a specific commit for reproducibility:
dsh plugin --profile web add github:Luke-Yong/dsh-plugin-knowledge-graph#<commit-sha>
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 →
ruvnet/ruflo
Tencent/WeKnora
EverMind-AI/EverOS
MemTensor/MemOS
plastic-labs/honcho
agentscope-ai/ReMe
zilliztech/memsearch
vshulcz/deja-vu