> 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/plugins-and-integrations/convai-unity-sdk/features/long-term-memory.md).

# Long-term memory

Long-term memory (LTM) lets Convai characters retain facts about individual users across separate conversation sessions. This section covers how the system works, how to enable it, how to manage user identity and records, and the complete scripting 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>How long-term memory works</strong><br>Understand the session lifecycle, memory scoping, deduplication, and how facts are extracted and injected.</td><td><a href="/pages/vmFTDbOMYC0TTWNIC7Nw">/pages/vmFTDbOMYC0TTWNIC7Nw</a></td></tr><tr><td><strong>Long-term memory quick start</strong><br>Enable LTM for a character and verify cross-session recall in the Unity Editor in three steps.</td><td><a href="/pages/jhH0HpubiAmSHgHB5acq">/pages/jhH0HpubiAmSHgHB5acq</a></td></tr><tr><td><strong>Configure memory for a character</strong><br>Toggle LTM on or off per character via the Convai dashboard or the CharacterService scripting API.</td><td><a href="/pages/lG0GNEfMD5jvoHOjCCax">/pages/lG0GNEfMD5jvoHOjCCax</a></td></tr><tr><td><strong>End-user identity</strong><br>Understand how the SDK identifies users and how to supply your own authentication-backed ID.</td><td><a href="/pages/GQgbZSFMOcRCBLwo1vqX">/pages/GQgbZSFMOcRCBLwo1vqX</a></td></tr><tr><td><strong>Manage end-user records</strong><br>Browse and delete end-user records from the editor or via the EndUsersService scripting API.</td><td><a href="/pages/09sxltM2pYC5cl7evTls">/pages/09sxltM2pYC5cl7evTls</a></td></tr><tr><td><strong>Memory management API</strong><br>Programmatically list, add, retrieve, and delete memory records for a user–character pair.</td><td><a href="/pages/3GS4gHtc1oXVknBcIakW">/pages/3GS4gHtc1oXVknBcIakW</a></td></tr><tr><td><strong>Long-term memory scripting reference</strong><br>Complete method signatures, parameters, return types, and data models for all LTM APIs.</td><td><a href="/pages/rNXGHpGQBdg9YBcHJ3hR">/pages/rNXGHpGQBdg9YBcHJ3hR</a></td></tr><tr><td><strong>Long-term memory usage examples</strong><br>Four complete patterns: zero-config persistence, authenticated identity, memory seeding, and reset.</td><td><a href="/pages/k71sbCPyoe2SjjSKXPAv">/pages/k71sbCPyoe2SjjSKXPAv</a></td></tr><tr><td><strong>Troubleshoot long-term memory</strong><br>Diagnose why memories aren't persisting and resolve Memory Management API HTTP errors.</td><td><a href="/pages/ljp5Ye0OhKTKJVYgfM50">/pages/ljp5Ye0OhKTKJVYgfM50</a></td></tr></tbody></table>

### Next steps

Start with [How long-term memory works](/api-docs/plugins-and-integrations/convai-unity-sdk/features/long-term-memory/how-long-term-memory-works.md) for a conceptual overview, then follow [Long-term memory quick start](/api-docs/plugins-and-integrations/convai-unity-sdk/features/long-term-memory/quick-start.md) to get memory running in your scene.


---

# 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:

```
GET https://docs.convai.com/api-docs/plugins-and-integrations/convai-unity-sdk/features/long-term-memory.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.
