dsh-classic-tools

DSH PLUGIN记忆与知识

仓库 MathieuPortmann/dsh-classic-tools

记忆与知识 L4 · 沙盒安装通过 安全审查:低风险 可信度:银 可安装插件
安装这个插件

dsh-classic-tools 是 MathieuPortmann 维护的 记忆与知识 类 DSH 可安装插件, 仓库为 MathieuPortmann/dsh-classic-tools,许可证 MIT。 下面按「装什么、怎么装、验没验过、跑起来要注意什么」逐项列出。

一句话选型结论

按资料字段整理

dsh-classic-tools 是记忆与知识类的 DSH 可安装插件,验证等级 L4 · 沙盒安装通过,安全审查为低风险,有可直接复制的安装命令。验证通过不等于安全:插件会读写文件、执行命令或联网,装前先到仓库确认它做了什么;涉及密钥或系统权限的,建议先在隔离环境试装。

分类记忆与知识 收录类型可安装插件 验证等级L4 · 沙盒安装通过 安全审查低风险
验证等级 L4 L4 · 沙盒安装通过
GitHub 星标 0 复刻 0 · 未关闭 issue 0
最近更新 2026-10-28 创建于 2026-10-25
README 10.2 KB 正文体量,越大说明说明书写得越细

安装

可安装插件
在 DSH 里执行,装完用 dsh plugin list 确认已挂上;标了 L4 / L5 的命令已在沙盒里真实跑通
dsh plugin --profile web add github:MathieuPortmann/dsh-classic-tools#v0.1.0
  1. 1
    确认版本与运行环境

    仓库没有标注兼容版本与 Node.js 要求,先确认你的 DSH 版本能装,再继续。

  2. 2
    执行安装命令

    在 DSH 里执行上面的命令;多包仓库要注意区分具体子包名,别装错包。

  3. 3
    确认已挂载

    用 dsh plugin list 查看列表里是否出现这个插件,出现即挂载成功。

  4. 4
    试跑并检查权限

    加载后跑一个最小用例,确认它能正常工作;同时看它申请了哪些文件、命令或网络权限。

兼容 DSH 版本未标注版本不匹配时安装会报错
Node.js 要求未标注来自仓库 package.json 的 engines 字段
前置依赖无需要同时安装的同级依赖
npm 包名未发布到 npm可用 npm view 查看包信息

能做什么

记忆与知识
字段来自项目仓库与公开索引,中文说明由本站标注

适用场景

联网搜索记忆

上游标签

deepseek-harnessdsh-pluginlocal-llmollamaweb-search

验证等级与安全审查

L4 · 沙盒安装通过
自动化流程结论,不是人工审核
验证等级L4 · 沙盒安装通过安装命令在隔离沙盒内真实执行成功,无依赖错误
安全审查低风险静态分析结论,未标注不代表已通过审查
仓库健康度活跃按仓库活跃度与最近更新时间给出
可信度银综合仓库活跃度与验证结果

选择建议

装之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 验证等级 L4:在沙盒里真实装过,依赖能装上,不是纸面声明。
  • 静态安全审查为低风险,没有发现明显可疑行为。
  • 有可直接复制的安装命令,不用自己翻文档找入口。

先想清楚的地方

  • 没有声明 Node.js 版本要求,版本不匹配可能装不上。
  • 验证通过不等于安全:插件会读写文件、执行命令或联网,装前先到仓库确认它做了什么。

更适合

  • 需要在记忆与知识场景里给 DSH 补能力的人。
  • 想装完就能用、不想自己排依赖的人。
  • 能接受在本地装依赖、愿意自己确认权限的人。

不太适合

  • 只使用 DSH 官方内置能力、不接受第三方插件的人。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
插件验证等级安全审查星标兼容版本安装命令
dsh-classic-tools当前 L4 · 沙盒安装通过 低风险 0 未标注 有
ruflo L3 · 安装规范通过 低风险 7.4 万 未标注 无
OpenViking L3 · 安装规范通过 低风险 3.9 万 未标注 无
WeKnora L4 · 沙盒安装通过 低风险 3.3 万 未标注 有
distilly L4 · 沙盒安装通过 低风险 2.5 万 未标注 有
EverOS L4 · 沙盒安装通过 低风险 1.3 万 未标注 有

仓库档案

记忆与知识
字段来自项目仓库与公开索引,中文说明由本站标注
作者 / 维护方MathieuPortmann仓库 dsh-classic-tools · 默认分支 main
分类记忆与知识memory
收录类型可安装插件声明了 dsh.bundle、可用 dsh plugin add 安装的条目
开发语言未标注仓库主语言
许可证MIT商用或二次分发前请确认条款原文
星标 / 复刻 / issue0 / 0 / 0收录时的数值,非实时
创建 / 更新2026-10-25 · 2026-10-28最后推送 2026-10-28
本站收录2026-10-30首次进入本站目录的时间

README 全文

10.2 KB
作者原文,中文版优先;只做安全转义,不改内容

dsh-classic-tools

Web search for local models and help for small context windows, for
DeepSeek Harness (DSH):

  • a Web: on / off chip next to the message box, with web search through your local
    Ollama;
  • a tool budget and a scratchpad that keep small-context models (about 49k tokens or
    less) on track;
  • two light modes, Ultralight and Advanced thinking.

> Maintenance: best-effort. Issues may go unanswered; forks are welcome.

What it adds

Web chip and /web

  • /web on | off | toggle | status, or click the Web chip in the message box. One switch for
    every conversation and every model, applied from the next message. The state is kept in
    /web-toggle.json. Web starts OFF until you turn it on.
  • OFF: the web tools are hidden from the model, so it never calls a dead tool.
  • ON:
  • DSH itself searches the web for each new message of yours (not left to the model's choice) and
    adds the results before the model answers. Greetings, panel passages and questions about
    your own notes ("my notes", "in my Logseq") are not searched.
  • Short research rules are added to the system prompt: answer from pages read, mark single-source
    facts "(unconfirmed)", end with a Sources section.
  • If the answer has no Sources section, the model is sent back once to add it.
  • web_search and web_fetch go through Ollama. web_fetch is replaced by web_read
    (below).

web_read

DSH's web_fetch returns the start of a page. web_read(url, question?, start?) instead cleans the
page (CSS and script leftovers, menus, repeated paragraphs, link targets), saves it in
/cache/web, splits it at headings, ranks the passages against the question with
BM25 (keyword scoring, no model) and returns the best ones, about 4000 characters, in page order.
The model can read other parts with another question or start=p7. A saved page is reused for 24 h
and deleted after 3 days.

Tool budget

On an agent whose context window is 49152 tokens or less (maxContextWindow), each family of tools
stays hidden until your messages mention it, and then stays available for the conversation. Larger
models keep every tool. A family is { id, tools: [tool names], words: "regular expression" }. The
defaults name the tools of the author's other plugins (Zotero, Logseq, documents, memory, tasks...);
tools that are not installed are skipped. Replace them in cordis.patch.yml:

- id: tool-budget
name: 'dsh-classic-tools/tool-budget'
config:
maxContextWindow: 49152
families:
- id: wiki
words: 'wiki|confluence'
tools: [wiki_search, wiki_page]

Scratchpad

For the same small-context models: tools step_done(step, learned), scratch_note(text),
scratch_read(name?). Notes are kept in /scratch// (state.md ledger,
steps/NN.md, notes.md, raw/ = full text of folded outputs, synthese.md = final answer). After
a step_done, long tool outputs (over 600 characters) are folded at the next step to a short head and
a pointer, the same replay-safe way as DSH's own tool-result pruner (the original stays in the
session log). The protocol and the ledger are re-sent with every request, so they survive
compaction. If you ask for the results in a folder ("save it in ~/reports"), a step that says it
wrote elsewhere is refused. Folders untouched for 7 days are removed at startup. Larger models do
not see these tools. The idea follows AgentFold and Context-Folding (2025), MemGPT's core memory and
Anthropic's memory tool.

Ultralight and Advanced thinking

Two agent modes with the smallest possible prompt for small models: no shell, no file changes, web
tools only while the Web chip is ON. Ultralight answers concisely; Advanced thinking asks for
step-by-step reasoning with self-checking (set Effort to "high" in the model menu).

The interface is in English, and in French when DSH's language is French. To translate the chip, add
a table next to en and fr at the top of client.js.

Install

dsh plugin --profile web add github:MathieuPortmann/dsh-classic-tools

Restart the profile afterwards. Requires Node ^22.19.0 || >=24 and DSH >=0.2.0-rc.2 <0.3.0 (see
Compatibility), and an Ollama that can answer web search and fetch requests (see
Permissions). Once the package is on npm,
dsh plugin --profile web add dsh-classic-tools works too.

Configuration

Everything has a default. Edit the rows in cordis.patch.yml (or your profile) to change:

Row Option Default Meaning
web-toggle skipSkills [] slash commands (names without /) that work only on your own text: a message using one gets no automatic search, for example [summarize, translate]
tool-budget maxContextWindow 49152 agents with a window up to this size get the tool budget
tool-budget families see above the hidden tool families
scratchpad maxContextWindow 49152 agents with a window up to this size get the scratchpad
scratchpad foldMinChars, foldHeadChars, ledgerMaxChars, nudgeAfterCalls, keepDays, dataDir 600, 240, 1600, 6, 7, /scratch folding and ledger sizes, reminder after N calls without step_done, days before cleanup, folder

Environment: OLLAMA_HOST (default http://127.0.0.1:11434), DSH_HOME (default ~/.dsh).

How it works

  • lib/web-toggle.js (host side) registers the Ollama providers, /web, the web_read tool, the
    research rules and the hooks; its pure rules are in lib/web-rules.js (search query, Sources
    detection, turn state).
  • lib/web-page.js is the web_read engine: cleaning, passages, BM25, cache. Pure JavaScript, no
    dependency. It is a port of native code; the port was compared with that code on about 140,000
    generated, fixture and real-page cases (cleaned text, chosen passages and cache files) with
    identical results.
  • lib/tool-budget.js, lib/scratchpad.js and lib/scratch-core.js (pure functions) hold the
    small-context helpers.
  • client.js (page side) draws the chip. It reads the state from the description of the /web
    command ("... - currently ON"), so showing the state leaves no line in the conversation (a click
    runs /web on or /web off, which shows one short line).
  • cordis.patch.yml adds the rows, the two modes and the web provider choice
    (searchProvider: ollama, fetchProvider: ollama). Removing the bundle removes all of it.

Compatibility

Component Supported
Node.js ^22.19.0 \|\| >=24.0.0 (engines.node)
DSH >=0.2.0-rc.2 <0.3.0; declared as optional peerDependencies on @deepseek-ai/dsh-llm, @deepseek-ai/dsh-tools and zod, the only packages loaded from the DSH installation
Platform Linux (tested); pure JavaScript, no native addon
Ollama a version that serves /api/experimental/web_search and /api/experimental/web_fetch (experimental endpoints that may change)

Tested with DSH 0.2.0-rc.2 on Node 22.23 (see Verification).

Permissions and external services

Everything the plugin can touch, and what happens when it fails:

Capability Where Used for If it fails
Network lib/web-toggle.js (fetch) POST to your Ollama (OLLAMA_HOST, default 127.0.0.1:11434): /api/experimental/web_search (the search query) and /api/experimental/web_fetch (a page URL). Ollama's web search and fetch are served through ollama.com (see Ollama's documentation), so your search queries and the URLs the model reads leave your computer through Ollama; the plugin sends nothing anywhere else, and only while Web is ON web search returns an error to the model; the automatic search puts a short "search failed" note in the context
Files lib/web-toggle.js, lib/web-page.js, lib/scratchpad.js, lib/scratch-core.js reads and writes /web-toggle.json (the switch; watched for changes), /cache/web/*.md (pages read by web_read; pruned after 3 days), /scratch// (scratchpad; cleaned after 7 days). No other file the switch reads as OFF; a page is not cached; scratchpad tools return an error
Commands none no child process, no shell n/a
Dynamic module loading lib/web-toggle.js, lib/scratchpad.js (importFromDsh) loads zod, @deepseek-ai/dsh-llm and @deepseek-ai/dsh-tools from the DSH installation that runs the plugin (a synchronous require of an ES module fails on Node 22). Nothing is downloaded and no code is evaluated from text (eval / new Function are not used) the plugin fails to load
Tools for the model web_read; step_done, scratch_note, scratch_read see above. web_read works only on http(s) URLs and says it is unavailable while Web is OFF an error text is returned
Command /web the switch usage error
Hooks agent/inbox/claimed, agent/pre-step, agent/turn-stopping, tools/pre-execute hide or show tools, add the automatic search results and the Sources reminder, fold old tool outputs, save the final answer each hook swallows its own errors so a turn is never blocked
Session log lib/scratchpad.js the scratchpad folds a long tool result by appending a compaction/prune event and a replacement tool/result event (nothing is deleted; the original stays in the log) the output stays unfolded
Interface client.js one chip in the message box; registers a French dictionary and language entry with DSH's locale service no chip

Verification

Checked on a disposable profile (DSH_HOME pointing at a temporary folder, so the real profile is
never touched):

npm pack
dsh plugin --profile t add file:$PWD/dsh-classic-tools-0.1.1.tgz   # install
dsh t --port 3095 --no-open                                         # start: rows load, no error
dsh plugin --profile t remove dsh-classic-tools                      # uninstall

npm test runs 23 standalone tests (the web_read engine, the Web rules, the tool budget, the
scratchpad core and the imposed-folder rule) with no DSH installation needed.

Develop

npm test

License

MIT

常见问题

6 问
答案由本站依据条目字段整理,不引用上游原文
dsh-classic-tools 怎么安装?

在 DSH 里执行 `dsh plugin --profile web add github:MathieuPortmann/dsh-classic-tools#v0.1.0` 即可。

dsh-classic-tools 的验证等级是什么意思?

L4 · 沙盒安装通过。安装命令在隔离沙盒内真实执行成功,无依赖错误

dsh-classic-tools 安全吗?

低风险。

dsh-classic-tools 装之前要先确认什么?

先看它会读写哪些文件、执行哪些命令、连接哪些网络地址;验证等级只说明装得上、跑得起来,不等于安全。涉及密钥或系统权限的,建议先在隔离环境试装。

dsh-classic-tools 用的是什么许可证?

上游标注为 MIT。商用或二次分发前请到仓库确认许可证原文。

这条记录的数据可靠吗?

本站按仓库名去重后合并整理,字段以作者仓库与 npm 元数据为准;安装命令、仓库地址与 README 保持原文,带 L4 / L5 标记的安装命令已在隔离沙盒里真实跑通。

记忆与知识
按星标排序,可作替代方案

ruflo

ruflo

L3 · 安装规范通过 7.4 万 星

OpenViking

OpenViking

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、`vik

L3 · 安装规范通过 3.9 万 星

WeKnora

WeKnora

把 WeKnora 知识库接入 dsh 的四个只读工具:列出知识库、混合检索原文片段、按顺序还原单篇文档,以及直接取用 WeKnora 自己

L4 · 沙盒安装通过 3.3 万 星

distilly

distilly

Distilly — Distill how they think into reusable Skills for any Agent o

L4 · 沙盒安装通过 2.5 万 星

EverOS

EverOS

L4 · 沙盒安装通过 1.3 万 星

MemOS

MemOS

L4 · 沙盒安装通过 1.2 万 星

MathieuPortmann 的其它插件

6 个

插件的元信息来自作者仓库;分类、验证等级与安全结论的中文说明为中文整理,最近核验 —。