05 - After Wiring Up TencentDB Agent Memory, Why I’m Still Reading About Mnemosyne OS

05 - 在接入 TencentDB Agent Memory 后，为什么我还在研究 Mnemosyne OS

Cover: accumulated project experience leading into the next handoff. AI-generated concept illustration. A note before we start: all five diagrams below carry Chinese labels; the English captions summarize what each one shows. 封面： 积累的项目经验如何引导至下一次交接。AI 生成的概念插图。在开始之前说明一下：下文中的五张图表均带有中文标签；英文标题概括了每张图表的内容。

The draft that made me restate the question In the previous post I finished digging into DSH’s plugin loading — DSH being the agent environment I’ve been working in across this series. Installing a plugin requires a restart; changing user configuration hot-reloads. They touch different layers. That post left two threads open: build a plugin myself, and go deeper on memory integration. I said I’d write whichever produced something worth telling first. 那篇让我重新审视问题的草稿 在上一篇文章中，我完成了对 DSH 插件加载机制的深入研究——DSH 是我这一系列文章中一直在使用的 Agent 环境。安装插件需要重启，而修改用户配置则支持热重载，它们触及的是不同的层级。上一篇留下了两个待办事项：自己动手构建一个插件，以及深入研究内存集成。我当时说，哪一个先产出值得分享的内容，我就写哪一个。

This time it’s memory — but the trigger was a draft that came back wrong. I handed my reference material to WorkBuddy and asked for a draft combining my recent study of TencentDB Agent Memory with ideas from Mnemosyne OS. It came back fast. The concepts were all there. There was even a table. It read like the real thing. The further I got, the more something felt off: it knew the topic “memory systems,” but it didn’t pick up why I had arrived there. The research from posts 01–04 receded into background. The structure of the reference article became the spine instead. Somebody else’s experience got rewritten in the first person as “mine.” 这次是关于内存——但触发点是一份写偏了的草稿。我将参考资料交给 WorkBuddy，要求它写一份草稿，结合我最近对 TencentDB Agent Memory 的研究以及 Mnemosyne OS 的理念。它很快就完成了。概念都在，甚至还有一张表格，读起来像模像样。但我越读越觉得不对劲：它确实懂“内存系统”这个主题，但它没理解我为什么会研究它。第 01 到 04 篇的研究成果被抛到了脑后，参考文章的结构反而成了主干。别人的经验被改写成了第一人称的“我的”经验。

I wanted post 05. What I got looked like a brand-new opening with little connection to what came before. That pushed me to restate the question: after all this time spent on agent memory, what exactly do I want the AI to remember for me? 我想要的是第 05 篇，但得到的却像是一个全新的开头，与之前的内容几乎没有关联。这促使我重新审视这个问题：在花了这么多时间研究 Agent 内存之后，我到底希望 AI 为我记住什么？

From “the tool can be called” to “the project can be continued” Looking back, the first four posts were all heading the same way. In 01 I studied TencentDB Agent Memory: how conversations settle into memory, how docs and code become reusable assets. In 02 I went to DSH’s source to understand how an agent environment carrying those capabilities is organized. In 03 I connected the two — proxies, addresses, tool calls, debugging layer by layer until the integration ran. In 04 I went further into plugins: how capability gets installed, how config takes effect, why some updates force a restart. 从“工具可被调用”到“项目可被延续” 回望过去，前四篇文章的方向是一致的。在 01 中，我研究了 TencentDB Agent Memory：对话如何沉淀为内存，文档和代码如何成为可复用的资产。在 02 中，我深入 DSH 源码，理解承载这些能力的 Agent 环境是如何组织的。在 03 中，我将两者连接起来——代理、地址、工具调用，一层层调试直到集成成功。在 04 中，我进一步研究了插件：能力如何安装，配置如何生效，为什么某些更新强制要求重启。

Figure 1: This post continues the memory thread left open in 04 and pushes toward “how does a project get handed over.” 图 1： 本文延续了 04 中留下的内存线索，并进一步探讨“项目如何进行交接”。

Post 03 had a moment I keep thinking about: the code graph was already built, but allocation reported the resource didn’t exist — asset registration hadn’t been completed. Finished content doesn’t mean the downstream consumption path works. So the “integration” road has moved forward. But in day-to-day work another need kept getting sharper: When I switch sessions — or switch agents — can work continue along the path the project already walked? 第 03 篇中有一个时刻我一直念念不忘：代码图谱已经构建完成，但分配时却报错资源不存在——资产注册尚未完成。内容完成并不意味着下游的消费路径是通畅的。所以，“集成”之路确实向前推进了。但在日常工作中，另一个需求变得愈发迫切：当我切换会话——或者切换 Agent 时，工作能否沿着项目已经走过的路径继续下去？

Take this article. A successor should at least know which problems the earlier posts covered and which step this one moves forward; which conclusions came from my own hands-on work and which from official documentation; what the reference articles inspired, and which narratives must not be passed off as my experience. Knowing that I’ve “been researching memory lately” is nowhere near enough. It has to take that context and produce the right next action. 以这篇文章为例。接手者至少应该知道前几篇文章涵盖了哪些问题，这一篇又推进了哪一步；哪些结论来自我的亲身实践，哪些来自官方文档；参考文章启发了什么，哪些叙述绝不能冒充为我的经验。仅仅知道我“最近在研究内存”是远远不够的。它必须利用这些上下文，并产出正确的下一步行动。

To be clear: this off-target draft was not a controlled comparison of memory products. I’m not claiming anything about which system recalls better. It just forced me to say my own requirement out loud. 需要明确的是：那份写偏的草稿并非对内存产品的对照测试。我并不是在断言哪个系统的召回效果更好。它只是迫使我大声说出了自己的需求。

Tencent line: integrated. Mnemosyne OS: still an open question Keep the two tracks separate. TencentDB Agent Memory — I’ve done real integration and debugging with it in the DSH scenario. Its official documentation explicitly puts memory storage, retrieval, and the access relationships between users, teams, and agents at the center of the product. [1] Tencent 路线：已集成。Mnemosyne OS：仍是一个待解的问题 保持两条路径独立。TencentDB Agent Memory——我已经在大模型 Agent 环境（DSH）中对其进行了实际的集成和调试。其官方文档明确将内存存储、检索以及用户、团队和 Agent 之间的访问关系置于产品的核心位置。[1]

Mnemosyne OS — so far I’ve only read GCat’s article about it. I have not independently verified it on the same kind of task. What caught my attention in that write-up is that it stores raw material and the index of descriptive material separately, and exposes precise location lookup, category lookup, and semantic search. [2] Whether the implementation actually delivers on that description in practice is something I have not yet verified on my side. The description maps onto something I need when writing: a summary helps me recall a conclusion quickly, but when I actually quote a number or confirm an operation, I need to get back to the material. A findable summary should also be able to walk me back to where the evidence lives. Mnemosyne OS——目前我只读过 GCat 关于它的文章。我还没有在同类任务中对其进行独立验证。那篇文章吸引我的是，它将原始素材与描述性素材的索引分开存储，并提供了精确的位置查找、类别查找和语义搜索功能。[2] 这种实现是否真的如描述所言，我尚未在实践中验证。这个描述正是我写作时所需要的：摘要能帮我快速回忆起结论，但当我真正引用数据或确认操作时，我需要回到原始素材。一个可检索的摘要，也应该能引导我回到证据所在的地方。

Figure 2: the verification path I want a successor to walk. This is a usage flow I’m proposing, not an architecture diagram of any product. 图 2： 我希望接手者遵循的验证路径。这是我提出的一种使用流程，而非任何产品的架构图。

Reading this, I added one more question for myself: When the project has already changed, is the memory the AI retrieves still fit to guide today’s action? “Found relevant content” is only the starting point. Next comes judging which project and which phase it applies to, and whether it has since been corrected. I once used a certain development approach and later changed it. The old record still has value — it explains why things were done that way. But if a new session acts directly on the old record, it drags the project backwards. That’s why I’m still reading about Mnemosyne OS: I want to follow the thread of how memory is organized and retrieved, and make my own handoff problem concrete. 读到这里，我为自己增加了一个问题：当项目已经发生变化时，AI 检索到的内存是否还适合指导今天的行动？“找到相关内容”仅仅是起点。接下来需要判断它适用于哪个项目、哪个阶段，以及它是否已经被修正。我曾经使用过某种开发方法，后来又改变了它。旧记录依然有价值——它解释了为什么当时要那样做。但如果新的会话直接基于旧记录操作，就会拖累项目进度。这就是我还在研究 Mnemosyne OS 的原因：我想顺着内存如何组织和检索的线索，将我自己的交接问题具体化。

I already hit this need while building my workbench Recently I’ve been turning my content workbench into a platform that can run on its own. When I first wrote the requirements, one thing mattered a lot: it must own its own flow, be easy to operate, run independently, and not depend on any single agent. Concretely: articles, revisions, publish tasks and execution results live in the application. When a scheduled task runs and what state it’s in is managed by the service. A model can help with writing, but if I turn that off, content management and publishing should still work. Finishing that let me separate two questions I’d been conflating: One: does the program per… 在构建工作台时，我已经遇到了这个需求 最近，我一直在将我的内容工作台转变为一个可以独立运行的平台。当我最初编写需求时，有一点非常重要：它必须拥有自己的流程，易于操作，独立运行，且不依赖于任何单一的 Agent。具体来说：文章、修订版本、发布任务和执行结果都应存在于应用程序中。定时任务何时运行及其状态由服务管理。模型可以辅助写作，但即使我关闭模型，内容管理和发布功能也应该正常工作。完成这些工作后，我得以将之前混淆的两个问题分离开来：第一：程序是否……