> For the complete documentation index, see [llms.txt](https://docs.convai.com/api-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/features/long-term-memory.md).

# 长期记忆

长期记忆（LTM）使 Convai 角色能够在不同的对话会话之间保留有关单个用户的事实。本节涵盖系统的工作原理、如何启用它、如何管理用户身份和记录，以及完整的脚本 API。

<table data-view="cards"><thead><tr><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>长期记忆的工作原理</strong><br>了解会话生命周期、记忆作用域、去重，以及事实如何被提取和注入。</td><td><a href="/pages/cb4d859b279841fc234bec92056ed917a73b519b">/pages/cb4d859b279841fc234bec92056ed917a73b519b</a></td></tr><tr><td><strong>长期记忆快速入门</strong><br>通过三个步骤为角色启用 LTM，并在 Unity 编辑器中验证跨会话回忆。</td><td><a href="/pages/d051c20fa3bb87461147abd07ac16642c7956362">/pages/d051c20fa3bb87461147abd07ac16642c7956362</a></td></tr><tr><td><strong>为角色配置记忆</strong><br>可通过 Convai 控制台或 CharacterService 脚本 API 按角色开启或关闭 LTM。</td><td><a href="/pages/b54beab8714c42a31356b3abe240c02692f3d79b">/pages/b54beab8714c42a31356b3abe240c02692f3d79b</a></td></tr><tr><td><strong>最终用户身份</strong><br>了解 SDK 如何识别用户，以及如何提供您自己的、基于身份验证的 ID。</td><td><a href="/pages/c12fc9539ece3543a049cf5c334655c9bb0a6a3c">/pages/c12fc9539ece3543a049cf5c334655c9bb0a6a3c</a></td></tr><tr><td><strong>管理终端用户记录</strong><br>可在编辑器中或通过 EndUsersService 脚本 API 浏览和删除终端用户记录。</td><td><a href="/pages/49cef55d22f33c0ffdf4893701cd5a6686bd7590">/pages/49cef55d22f33c0ffdf4893701cd5a6686bd7590</a></td></tr><tr><td><strong>记忆管理 API</strong><br>以编程方式列出、添加、检索和删除用户-角色对的记忆记录。</td><td><a href="/pages/0b7e1084a14c3bcf13fec179ad83b458f07ecff4">/pages/0b7e1084a14c3bcf13fec179ad83b458f07ecff4</a></td></tr><tr><td><strong>长期记忆脚本参考</strong><br>所有 LTM API 的完整方法签名、参数、返回类型和数据模型。</td><td><a href="/pages/9c55a31cd790424665e521972bff5affc2dbe7f9">/pages/9c55a31cd790424665e521972bff5affc2dbe7f9</a></td></tr><tr><td><strong>长期记忆使用示例</strong><br>四个完整模式：零配置持久化、经身份验证的身份、记忆初始化，以及重置。</td><td><a href="/pages/d41fbdd4f21a090aa6d7e39be7a7eb215d0435c2">/pages/d41fbdd4f21a090aa6d7e39be7a7eb215d0435c2</a></td></tr><tr><td><strong>排查长期记忆问题</strong><br>诊断记忆未能持久保存的原因，并解决记忆管理 API 的 HTTP 错误。</td><td><a href="/pages/7a63a06da6d31beb01ce563b8e8b3398f3436122">/pages/7a63a06da6d31beb01ce563b8e8b3398f3436122</a></td></tr></tbody></table>

### 下一步

从……开始 [长期记忆的工作原理](/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/features/long-term-memory/how-long-term-memory-works.md) 先了解概念概览，然后继续 [长期记忆快速入门](/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/features/long-term-memory/quick-start.md) 以便让记忆在您的场景中运行。


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/features/long-term-memory.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.