Scorp1o117/dsh-tdai-memory

Name: Scorp1o117/dsh-tdai-memory
Author: Scorp1o117

Plugin插件 Native原生 ⭐ 7 MIT Memory & Knowledge记忆与知识库

Agent memory for DeepSeek Harness | DeepSeek Harness 记忆插件

Project Overview项目介绍

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

dsh-tdai-memory is a native DeepSeek Harness plugin that ports the open-source TencentDB Agent Memory four-layer memory system to DSH. It is part of the DeepSeek Harness Enhancement Suite, and can be installed directly via DSH’s built-in plugin command with a single line: dsh plugin --profile web add dsh-tdai-memory. The plugin automatically captures every conversation turn, extracts structured facts, user preferences, and events from conversations in a background pipeline, then injects relevant recalled memories into the prompt context for every new user message. It also exposes two dedicated search tools for querying raw conversation logs and structured memory records respectively.

This plugin is designed for DeepSeek Harness users who want to add persistent long-term memory capabilities to their AI agents. After installation and initial configuration, it runs automatically in the background without requiring manual user input between conversation turns. Every conversation turn is written to persistent raw storage, and a background pipeline uses an LLM to extract structured facts, preferences, and events from unstructured conversation content. When a user sends a new message, the plugin automatically retrieves relevant memories from the stored database and injects them into the agent’s prompt context, so the model can reference past user information without explicit prompting.

dsh-tdai-memory is released under the permissive MIT open-source license. Version 0.2.13 and newer require DSH version 0.1.0-rc.7 or newer, while users running older DSH 0.1.0-rc.6 must pin their installation to version 0.2.11, the last compatible release. Any changes to the plugin’s configuration require a full restart of DSH to take effect, because the core TDAI memory system is only initialized once at application startup. An optional dependency, node-llama-cpp, is required only for fully local embedding backends, and must be installed manually by the user due to native build approval requirements. There are also known trade-offs: deepseek-v4-flash produces non-compliant JSON for memory extraction, so mimo-v2.5 is the recommended default model, and deduplication is off by default due to output parsing instability.

dsh-tdai-memory 是专为 DeepSeek Harness（DSH）开发的原生记忆插件，属于 DSH 增强套件的一部分，它将腾讯云开源的四层 TDAI 记忆系统移植到了 DSH 平台中。该插件实现了从对话捕获、结构化记忆提取到自动召回注入的全流程能力，会在每次 prompt 组装时把匹配的记忆和用户画像注入动态上下文。插件可通过 DSH 内置的插件命令直接安装，兼容 DSH 的配置和配置管理体系。

该插件面向需要长期对话记忆能力的 DSH 用户，支持将用户过往对话中的偏好、事实和事件持久化存储，让 DSH 智能体能够记住用户的长期信息。在用户和智能体对话时，插件会自动捕获每一轮对话，后台流水线提取结构化信息，并在后续对话中自动召回匹配的记忆注入上下文。用户也可以通过插件提供的两个工具分别搜索原始对话和结构化记忆内容。

该插件采用 MIT 许可证开源，版本 0.2.13 及以上要求 DSH 版本不低于 0.1.0-rc.7，旧版本 0.1.0-rc.6 用户需要固定安装 0.2.11 版本。修改插件配置后需要重启 DSH 才能生效，若选择本地嵌入后端，需要手动安装可选依赖 node-llama-cpp。目前已知 deepseek-v4-flash 提取 JSON 不合格，结构化记忆去重功能输出不稳定，默认关闭。

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：dsh-tdai-memory（Scorp1o117/dsh-tdai-memory）
仓库：https://github.com/Scorp1o117/dsh-tdai-memory
本站详情页：https://www.yhbd.top/plugins/scorp1o117-dsh-tdai-memory/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 7 · 最近提交 2026-09-30 · 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 7 stars - very few users, little community feedback星标只有 7，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 desktop add dsh-tdai-memory@0.3.6

把 Scorp1o117/dsh-tdai-memory 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

8.0 KB · 缓存于 2026-09-30 22:10:44 · 8.0 KB

dsh-tdai-memory

Configuration page (DSH 0.2.0-rc.2 and later)

Open Plugins → Installed → dsh-tdai-memory from the homepage sidebar to configure and save this plugin. The page uses the official plugins.bundle.config interface, without a duplicate entry in global Settings. Web and Desktop share the page. This version requires DSH 0.2.0-rc.2 or a later 0.2.x host; existing configuration is retained.

GitHub: Scorp1o117/dsh-tdai-memory · npm: dsh-tdai-memory

Part of the DeepSeek Harness Enhancement Suite — Vision · Soul/Persona · Long-term Memory · Plugin Marketplace.

A port of TencentDB Agent Memory (Tencent Cloud's open-source four-layer memory system, originally an OpenClaw plugin) into DeepSeek Harness.

Compatibility (v0.4.1)

Verified with DSH 0.1.7-rc.2 (Web) and 0.2.0-rc.2 (Desktop runtime) in isolated profiles. The Desktop app uses its own desktop profile. Other DSH prereleases remain unverified.

Desktop install

Use the Desktop-installed dsh command (Application → Manage dsh Command), or the app’s Plugins page. Then install into the Desktop profile:

dsh plugin --profile desktop add dsh-tdai-memory@0.3.6

Restart the Desktop app to load the client bundle. Desktop keeps its profile under $DSH_HOME/profiles/desktop.

Features

L0 conversation capture: every turn (turn end, request boundary) is written to raw conversation storage (JSONL + SQLite + FTS + vectors)
L1 structured memory: a background pipeline uses an LLM to extract facts / preferences / events (persona / episodic / instruction) from conversations, stored in records/ + SQLite + FTS + vectors
L2 scenes / L3 persona: scene blocks and user profile generation (pipeline-scheduled)
Automatic recall injection: on every prompt assembly, relevant memories and the user profile are retrieved by the current user message and injected as dynamic context (the model "just remembers")
Tools: tdai_memory_search (L1 structured search), tdai_conversation_search (L0 raw-text search)

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 Scorp1o117/dsh-tdai-memory 的 README.md。在 GitHub 查看原文 →