shayexiangpaimeng/dsh-memory
Append-only layered memory plugin for DeepSeek Harness: five-layer partitioning, write gate, keyword recall, claim-anchors verification
Project Overview项目介绍
This is a community plugin for DeepSeek Harness that provides append-only five-layer partitioned durable memory for agents. It supports write validation, keyword recall and claim-anchor verification. Use it when you need long-term traceable agent memory. It currently only supports keyword-based recall, not vector search.
这是DeepSeek Harness代理的追加式分层持久记忆插件,支持五层分区存储、写入校验、关键词召回和声明锚点验证,需要为代理保留长期可追溯记忆时使用,注意当前仅支持关键词召回,不支持向量搜索。
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-memory(shayexiangpaimeng/dsh-memory)
仓库:https://github.com/shayexiangpaimeng/dsh-memory
本站详情页:https://www.yhbd.top/plugins/shayexiangpaimeng-dsh-memory/
本站登记:类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 2 · 最近提交 2026-09-24 · 主语言 TypeScript · 未检测到 DSH 插件清单
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
- No DSH plugin manifest detected - it may only carry the dsh-plugin topic, so the install method must be confirmed on the spot未检测到 DSH 插件清单:可能只是打了 dsh-plugin 话题,安装方式要现场确认
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:shayexiangpaimeng/dsh-memory
把 shayexiangpaimeng/dsh-memory 加入你的 DSH 配置(web profile)即可启用。
READMEREADME
@shayexiangpaimeng/dsh-memory
Append-only layered memory for DeepSeek Harness agents.
上下文会缩,记忆不该缩。
A community plugin (dsh-plugin) that gives an agent a durable, append-only
memory stream with five-layer partitioning, a write gate, keyword recall,
time-axis reads, and claim-anchors verification. Built by a deep user of
DeepSeek Harness, as a generalized, privacy-free re-implementation of the
memory system that has kept a companion AI continuous since the memory system
was first built (August 2026).
What it does
- Append-only write stream — every append writes one JSONL line; history is never rewritten.
- Five-layer partitioning —
permanent(never forget) /session(this session) /rolling(recent context) /config(configuration) /ephemeral(not saved). - Write gate — empty events, unknown layers, unknown statuses and orphan supersedes pointers are rejected or flagged before they can rot the stream.
- Claim-anchors verification — a fix claim ("已修复…") without an
anchor(measured value / checksum / command output) is flagged as a warning: claim detached from the disk = diagnosed defect, not a slip. - Whole-stream anchor audit (
memory_audit) — write-time warnings are a soft constraint, because a claim can be rephrased as a plain statement. The audit reads the file, so it cannot be talked around. - Time-axis read (
memory_recent) — newest first, with an optional time window and keyword filter. Keyword recall cannot answer "what is the latest" or "how long has this been untouched": those words never appear in the entries. - Retirement and replacement chain — retract a conclusion without rewriting
it: append a new entry with
supersedes: <old ts>, optionally mark the old onestatus: retired. Retired entries stay in the stream for audit but are filtered out of the injected summary, so a withdrawn claim cannot come back as a current fact. - Prompt state rendering — a dynamic
memory:statesection renders the recent permanent + session layers at each assembly, from a cache warmed once at startup (read-once-per-session holds after warm-up). - Keyword recall — case-insensitive substring scoring, newest first.
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 →
vshulcz/deja-vu
adoresever/graph-memory
mnemon-dev/mnemon
Phant0Meow/dsh-meow-memory
slow-stack/mneme
Aik358/dsh-auto-memory