YYTbit/dsh-plugin-meta-memory
DeepSeek Harness的结构化长期记忆系统
Project Overview项目介绍
dsh-plugin-meta-memory is a native long-term memory plugin built exclusively for DeepSeek Harness (DSH). It implements a structured memory system that helps DSH agents organize and retain information across long-running projects. The system organizes memories into named units following the verb-modifier-noun convention, stores each memory as both a brief scanable version and a detailed full version, maintains a global index automatically, and injects relevant brief memories into the agent’s context automatically. To install the plugin, you can run the command dsh plugin --profile your-profile add dsh-plugin-meta-memory directly from the DSH CLI.
This plugin is designed for developers working on long-term projects that need persistent knowledge retention. When integrated into a DSH workflow, the agent automatically creates a .meta-memory directory in your project root to store all memory records. Brief memory versions are automatically injected into context for relevant queries, while full detailed versions are only loaded when explicitly requested. Users can also interact with the memory system via a built-in CLI tool that supports initializing the memory directory, listing units, searching for keywords, reading records, and displaying the global index.
The plugin is released under the permissive MIT open source license, so you can use or modify it freely for any purpose. No additional external dependencies are required to run the plugin, as it is built specifically for the DSH environment. You can customize a small set of configuration options through your DSH config file, including the memory storage path, whether to enable auto-injection and the skill, and the maximum byte size for injected brief memories. The default memory storage path is ~/.dsh/meta-memory.
这是一款专门为 DeepSeek Harness 开发的原生结构化长期记忆插件,它为 DeepSeek Harness 代理提供了一套规范化的记忆组织系统,将记忆按照单元分类存储,每个记忆分别保存简要版和完整版,自动维护全局故事索引,还能自动将相关记忆的简要内容注入到对话上下文中,帮助代理保留长期项目信息。你可以通过 DSH 内置的 CLI 工具一键安装,命令为 dsh plugin --profile 你的配置档 add dsh-plugin-meta-memory。
这款插件主要面向需要维护长期项目记忆的开发人员,在日常使用中,代理会自动在项目目录下创建 .meta-memory 文件夹,按照 动词-修饰词-名词 的命名规则生成记忆单元,每个记忆单元下分别存储简要记忆和完整记忆,简要记忆用于快速上下文注入,完整记忆则按需加载。用户还可以通过内置的 mm CLI 工具手动初始化、列出、搜索、读取记忆内容,查看全局索引。
该插件采用 MIT 许可证开源,无需额外依赖即可运行在 DeepSeek Harness 环境中。用户可以通过配置文件自定义记忆存储路径,设置是否开启自动上下文注入、是否启用技能,还能调整注入简要记忆的最大字节数。默认存储路径为 ~/.dsh/meta-memory,开启自动注入后会自动匹配相关记忆注入上下文。
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-meta-memory(YYTbit/dsh-plugin-meta-memory)
仓库:https://github.com/YYTbit/dsh-plugin-meta-memory
本站详情页:https://www.yhbd.top/plugins/yytbit-dsh-plugin-meta-memory/
本站登记:类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 4 · 最近提交 2026-08-14 · 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 dsh-plugin-meta-memory
把 YYTbit/dsh-plugin-meta-memory 加入你的 DSH 配置(web profile)即可启用。
READMEREADME
dsh-plugin-meta-memory
Structured long-term memory system for DeepSeek Harness.
What it does
Teaches the agent how to organize memories using a structured system:
- Units: Work categories named
verb-modifier-noun.unit - Records: Each memory has a brief (quick scan) and full (detailed) version
- Index: Self-maintained global storyline
- Auto-injection: Relevant briefs are injected into context automatically
Install
dsh plugin --profile your-profile add dsh-plugin-meta-memory
How it works
Memory structure
.meta-memory/
├── index.md
└── units/
├── debug-auth-module.unit/
│ ├── 0.token-refresh-fail.brief.md
│ └── 0.token-refresh-fail.full.md
└── read-deeplearning-paper.unit/
├── 0.transformer-attention.brief.md
└── 0.transformer-attention.full.md
Brief format (injected into context)
# token-refresh-fail
JWT token refresh returns 401 due to timestamp offset calculation error.
Full format (loaded on demand)
# token-refresh-fail
## Context
Auth module was failing on token refresh after 1 hour.
## Finding
expiresAt calculated using milliseconds instead of seconds.
## Evidence
src/auth/refresh.ts:42 - Math.floor(Date.now() / 1000) fixes it.
## Relevance
Any JWT/token related debugging in the future.
CLI tool
mm init # Initialize memory directory
mm list # List all units and records
mm read <unit> # Read all briefs in a unit
mm search <query> # Search briefs by keyword
mm index # Show the index
Configuration
- id: meta-memory
name: dsh-plugin-meta-memory
config:
memoryPath: '~/.dsh/meta-memory'
enableInjection: true
enableSkill: true
maxBriefBytes: 4096
License
MIT -- YYTbit
ruvnet/ruflo
Tencent/WeKnora
EverMind-AI/EverOS
MemTensor/MemOS
plastic-labs/honcho
agentscope-ai/ReMe
zilliztech/memsearch
vshulcz/deja-vu