solknight48/dsh-memoryhub
MemoryHub(mh)插件用于DeepSeek Harness(dsh):在会话开始时自动加载检查点记忆,添加mh_*工具和mh技能,并在Web UI中增加“记忆”选项卡。
Project Overview项目介绍
This is a DSH-native plugin that integrates the MemoryHub git-versioned project memory system into DeepSeek Harness. It ships a DSH bundle manifest, so it can be installed directly via the DSH CLI with the command dsh plugin --profile web add github:solknight48/dsh-memoryhub. It adds core integration features including auto-loading of MemoryHub checkpoints on DSH session start, six wrapped MemoryHub CLI tools, a dedicated Memory tab for the DSH web UI, and a runtime workflow skill for the LLM. It relies on the standalone mh CLI being installed and available on the system PATH, and additionally requires Git 2.32 or newer and Python 3.12 or newer to function correctly.
This plugin is built for developers who need to persist project context memory across multiple DSH sessions. It solves the problem of DSH native sessions not retaining memory between restarts or different work sessions. When a new DSH session starts, the plugin automatically loads existing MemoryHub checkpoints and injects the memory into the model's context before the first turn. During or at the end of a session, it automatically converts the DSH session event log into a compatible MemoryHub format and saves it to the versioned checkpoints. The LLM can directly call the built-in tools to search, list, check, and manage stored memory without shelling out to the command line.
All core features of this plugin have been verified via a full end-to-end test suite that exercises the key integration paths. Version 1 of the plugin does not support bridging steering messages or file attachments from DSH sessions to MemoryHub, though compact summaries can include any important content. The plugin is released under the open-source MIT license, and all source code is hosted publicly on GitHub. If you want to contribute or test changes locally, you can clone the repo, run npm install, then npm run build and npm test to verify your changes.
这是一个专为DeepSeek Harness(DSH)打造的原生插件,用于将MemoryHub版本化项目记忆系统集成到DSH工作流中。它支持在会话启动时自动加载MemoryHub检查点记忆,封装了六个常用MemoryHub CLI工具供大模型调用,还为DSH的网页界面添加了专用的Memory标签页,可查看当前工作区的检查点映射。可通过DSH CLI命令 dsh plugin --profile web add github:solknight48/dsh-memoryhub 完成安装。
该插件面向需要在DSH多轮会话中持久化保存项目上下文记忆的开发者,解决了DSH原生会话无法跨会话持久化保留项目记忆的问题。典型工作流为:新会话启动自动加载已有记忆注入上下文,大模型可直接调用工具搜索、列出、检查、管理记忆,会话进行中或结束时自动将当前DSH会话日志转换为兼容格式保存到MemoryHub检查点。
该插件要求预先安装MemoryHub CLI(即 mh 命令)并将其加入系统PATH,还依赖不低于2.32版本的Git和不低于3.12版本的Python。当前v1版本暂不支持桥接DSH会话中的引导消息和文件附件,整个项目采用MIT许可证开源,核心功能已通过完整端到端测试验证。
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-memoryhub(solknight48/dsh-memoryhub)
仓库:https://github.com/solknight48/dsh-memoryhub
本站详情页:https://www.yhbd.top/plugins/solknight48-dsh-memoryhub/
本站登记:类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 2 · 最近提交 2026-08-15 · 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 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 --profile web add github:solknight48/dsh-memoryhub
把 solknight48/dsh-memoryhub 加入你的 DSH 配置(web profile)即可启用。
READMEREADME
dsh-memoryhub
English | 简体中文
MemoryHub (mh) integration for
DeepSeek Harness (dsh).
MemoryHub keeps project memory as purified sessions in git-versioned
checkpoints under .memoryhub/. This plugin wires that into dsh:
- Auto-load on session start — runs
mh loadin the session workspace and injects the checkpoint memory as durable plugin context. No prompt, no tool call; the model simply starts with its memory back. mh_savebridges dsh sessions to mh — dsh session files are not among the transcript formats mh discovers (Claude Code / pi / Codex), so the plugin renders the live session's durable event log as a pi-format JSONL transcript (in the temp dir) and saves through mh's existing--transcriptpath. Purified saves and agent-written compact saves both work, under a stable per-session identity: re-saving replaces, never duplicates.- Six tools —
mh_load,mh_save,mh_status,mh_list,mh_search,mh_checkpointwrap the CLI; the model never has to shell out for the common operations. Rarer operations (mh link,mh back,mh import,mh ui) stay in the shell, as the skill explains. - A "Memory" tab in the web UI — beside chat and trajectory: the
mh uicheckpoint map of the session's workspace, embedded live (see The Memory tab). - The
mhworkflow skill — registered at runtime, it teaches the model when to load, when and how to save (including writing compact summaries), and the hub rules (no HANDOFF.md files,git -C .memoryhubfor anythingmhdoes not cover).

Prerequisites
mh installed and on PATH (uv tool install git+https://github.com/solknight48/memoryhub;
needs git ≥ 2.32, Python ≥ 3.12). The plugin shells out to it — the hub
format, git commits, and error wording stay owned by mh.
Install
dsh plugin --profile web add github:solknight48/dsh-memoryhub
The package declares dsh.bundle, so the install appends its patch layer to
the profile. For a checkout instead: dsh plugin --profile web add ./dsh-memoryhub.
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 →
JunNanLYS/dsh-layered-memory
EverMind-AI/EverOS
MemTensor/MemOS
plastic-labs/honcho
vshulcz/deja-vu
adoresever/graph-memory
mnemon-dev/mnemon