Spirtxiaoqi7/mindspace-dsh-session-memory

Name: Spirtxiaoqi7/mindspace-dsh-session-memory
Author: Spirtxiaoqi7

Plugin插件 Native原生 ⭐ 3 MIT Memory & Knowledge记忆与知识库 Sessions & Context会话与上下文 Prompts & Skills提示词与技能

适用于DeepSeek Harness的可编辑、会话隔离的个性化记忆功能

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

This is a native DSH plugin built exclusively for DeepSeek Harness, designed to separate work and everyday chat into two distinct memory contexts for the same user and assistant. It stores persistent information including people, relationships, user preferences, assistant identity, current user state, and lasting experiences beyond what standard context summaries can retain. To install from source, you clone the repository, install dependencies with corepack pnpm, build the plugin package, then add the compiled tgz file to your DSH web profile, and restart DSH to activate it. Version 0.7 targets DSH 0.1.5-rc.2 and 0.1.x APIs, so you need to match your DSH version to avoid compatibility issues.

To use the plugin, you select the Chat or Work chip in the DSH composer to switch between the two memory contexts based on your current task intent. The model will also automatically switch contexts when your main intent changes, and neither mode disables tools or alters permission settings. You can access the memory center through DSH’s Settings > Personalization menu to inspect, edit existing memory entries, inherit memory into a new blank session, change the compaction policy, or trigger manual compaction. Cross-context facts are stored in a neutral bridge staging area, and only merged or dismissed once you switch to the target context.

Memory maintenance runs after compaction, not after every conversation turn, so it only incurs minimal additional model usage. You can configure a dedicated lower-cost model for maintenance tasks, and if there are concurrent edits, it retries against the latest memory state with a maximum of three attempts per batch. All user memory data is stored locally in the DSH_HOME/mindspace-session-memory directory, and legacy data from older plugin versions can be automatically migrated to the new format. The plugin is released under the MIT license, and it is recommended that you back up your DSH_HOME directory before upgrading.

这是一个专为DeepSeek Harness（DSH）开发的原生会话记忆插件，核心功能是为用户分离工作和日常聊天两种独立的记忆上下文，分别存储人物关系、用户偏好、助手身份、当前状态和长期体验等持久信息，超越普通上下文摘要，维持长周期会话记忆。插件支持从源码编译安装，安装后需要在DSH配置文件中自定义参数，修改完成后重启DSH即可生效。

用户可通过DSH界面合成器的「Chat / Work」切换标签，根据当前任务意图切换对应的记忆上下文，两种模式都不会禁用工具或修改权限。在设置的个性化选项中，用户可以查看、编辑记忆内容，将现有记忆继承到新会话，修改压缩策略，也可以手动触发记忆压缩操作。

插件采用独立的记忆维护流程，压缩后会调用单独模型校验更新记忆，不会在每次对话后额外消耗token，支持配置专用的低成本模型进行维护，最多重试三次维护任务，不会阻塞普通对话。插件遵循MIT许可，现有旧版本数据可自动迁移，升级前建议备份DSH_HOME目录，不要同时加载旧版实现。

View on GitHub在 GitHub 查看

Send to your DSH发给你的 DSH 安装

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：mindspace-dsh-session-memory（Spirtxiaoqi7/mindspace-dsh-session-memory）
仓库：https://github.com/Spirtxiaoqi7/mindspace-dsh-session-memory
本站详情页：https://www.yhbd.top/plugins/spirtxiaoqi7-mindspace-dsh-session-memory/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 3 · 最近提交 2026-09-14 · 主语言 JavaScript

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。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意

Only 3 stars - very few users, little community feedback星标只有 3，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:Spirtxiaoqi7/mindspace-dsh-session-memory

把 Spirtxiaoqi7/mindspace-dsh-session-memory 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

4.7 KB · 缓存于 2026-09-14 19:40:13 · 4.7 KB

Mindspace Memory for DeepSeek Harness

中文 · Community plugin · MIT

Separate work from everyday conversation. Maintain memory beyond context summaries.

Chat and Work are two memory contexts for the same user and assistant, not two tool-permission presets. Each stores people, relationships, preferences, assistant identity, current state and lasting experiences.

What's new in 0.7

Independent maintenance after compaction. The main model can still write memory, but is no longer solely responsible for remembering. After successful compaction, a separate model call reconciles existing memory against the original conversation captured before summarization.
Updates instead of blind accumulation. Maintenance adds durable omissions, corrects superseded facts and merges duplicates. Absence from recent conversation is not a deletion reason.
No shortest-card eviction. Each card section supports up to 100 entries. Exceeding three entries no longer removes the shortest one.
Settings inheritance. Create a blank session with the current Chat/Work memories, people, identity, bridge and compaction policy, without copying conversation history.
General current state. Appearance or clothing may be described here, but is not a required dedicated feature.

Interaction

Use the composer Chat / Work chip to express the current context. The model may also switch when the main intent changes. Modes never disable tools or alter permissions.

In Settings → Personalization, inspect/edit memory, inherit it into a new session, change the compaction policy or compact manually.

Cross-context facts are staged in a neutral bridge: a short transition note (up to 300 characters) plus pending write instructions. Only after entering the target mode does the model merge or dismiss each pending item.

Maintenance lifecycle

Compaction captures the original textual conversation since the last successful compaction. On success, a separate request receives this evidence and current memory, then proposes source-linked operations. Long conversations are processed in ordered batches rather than truncated.

Memory revisions are checked before applying changes. Concurrent edits cause a retry against the latest state; cross-mode changes remain staged. Failed calls preserve memory and task evidence, with up to three attempts per batch. Background maintenance does not block ordinary conversation.

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 →

渲染基于仓库 Spirtxiaoqi7/mindspace-dsh-session-memory 的 README.md。在 GitHub 查看原文 →