tancheng33/dsh-ontology
DeepSeek Harness的类型化推理本体论(TBox + ABox)插件——代理声明、断言并依据模式约束查询的持久领域知识。
Project Overview项目介绍
dsh-ontology is a native plugin built exclusively for DeepSeek Harness that adds typed, schema-constrained ontology capabilities to DSH agents. Most agent memory systems store unstructured free text, which often leads to conflicting or inconsistent claims that go undetected by the agent. This plugin fixes that issue by requiring agents to adhere to a defined vocabulary, validating every claim before it is stored, and deriving implied facts instead of storing redundant copies. You can install it directly via the DSH CLI by running dsh plugin --profile <name> add dsh-ontology, or install it from source by adding the GitHub repository directly.
The plugin ships with four core commands: ontology_define to declare classes and typed relations, ontology_assert to store validated entities and facts, ontology_query to look up, traverse, and infer knowledge, and ontology_retract to remove facts with dependency protection. It supports multiple configuration options, letting users override settings like domain name, strict validation mode, inference enabling, maximum prompt terms, query result limits, and entity/fact capacity guards. You can run multiple isolated ontology graphs in a single DSH profile by adding separate configuration entries for each graph, which lets you keep different knowledge domains completely separate.
The plugin is released under the open source MIT license, and requires DeepSeek Harness version 0.1.0-rc.6 or newer, plus Node version 22.19 or 24 and above. It includes its own storage stack that works out of the box with a fresh DSH profile, and stores all ontology data in $DSH_HOME/storages/<domain>.json. The core rule engine is also available as a standalone import, so you can use its inference and validation capabilities outside of DeepSeek Harness if needed for your own projects.
这是一个专为 DeepSeek Harness 开发的原生插件,为 DSH 代理提供基于本体的结构化知识记忆系统。和无结构的自由文本记忆不同,它会强制实施模式约束,验证所有存储的知识,防止代理存储相互矛盾或不一致的断言,可直接通过 DSH 内置插件命令完成安装。
它提供四个核心工具:ontology_define 定义本体类和关系,ontology_assert 验证并存储实体和事实,ontology_query 支持查询、推理和遍历,ontology_retract 支持安全删除知识并处理依赖。用户可通过配置文件调整存储域名、严格模式、推理开关、查询结果上限等多项参数。
该插件基于 MIT 许可证开源,要求 DeepSeek Harness 版本不低于 0.1.0-rc.6,Node 版本需要 22.19 或 24 以上。它自带存储栈,可在空配置文件中直接运行,核心规则引擎也可单独抽离,在 DeepSeek Harness 外部使用。
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-ontology(tancheng33/dsh-ontology)
仓库:https://github.com/tancheng33/dsh-ontology
本站详情页:https://www.yhbd.top/plugins/tancheng33-dsh-ontology/
本站登记:类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 15 · 最近提交 2026-08-16 · 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。
- 15 stars - an early-stage project星标 15,属于早期项目
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 dsh-ontology
把 tancheng33/dsh-ontology 加入你的 DSH 配置(web profile)即可启用。
READMEREADME
dsh-ontology
English | 中文
A typed, inference-capable ontology for DeepSeek Harness — durable domain knowledge the agent declares, asserts against, and queries under schema constraints.
Most agent memory is a bag of strings: the agent writes prose, later reads prose, and nothing ever tells it that what it just recorded contradicts what it recorded last week. This plugin gives the agent a vocabulary it must respect. You declare what kinds of things exist and how they may relate; every claim is then checked against that model before it is stored, and claims that follow from other claims are derived rather than repeated.
ontology_define declare classes and typed relations (the TBox)
ontology_assert record entities and facts (the ABox, validated)
ontology_query look things up, traverse, infer
ontology_retract remove, with dependency protection
Why a TBox, not a notes file
| notes-style memory | dsh-ontology | |
|---|---|---|
| Structure | free text | classes, typed relations, entities, triples |
| Bad input | silently stored | rejected, naming the constraint it broke |
| Implied facts | restated by hand, drift apart | derived on read from transitive / symmetric / inverseOf |
| Retraction | orphaned prose lingers | facts cascade with their entity; derived facts vanish with their premise |
| Reading it back | grep and hope | query by class (subclass-aware), triple pattern, neighbourhood, or shortest path |
The constraint is the point. When the agent asserts ada depends_on api and depends_on is declared Component -> Component, it gets back:
REJECTED ada depends_on api: ada is not in the domain of depends_on
(requires one of: Component; has: Person)
That is a real signal — either the claim is wrong, or the model of the domain is incomplete. Free-text memory can produce neither.
Install
dsh plugin --profile <name> add dsh-ontology
dsh --profile <name>
Or from a checkout / git host:
dsh plugin --profile <name> add ./dsh-ontology
dsh plugin --profile <name> add github:tancheng33/dsh-ontology
A
github:install builds from source, so pnpm ≥10 needs the build allowlisted. AddallowBuilds: { dsh-ontology: true }to the profile'spnpm-workspace.yamland re-run, and pin a commit (#<sha>) so a later push cannot silently change what runs. Installing from npm needs no allowance.
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