> 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-unreal-engine-plugin/features/long-term-memory.md). # Long-term memory Long-term memory (LTM) lets a Convai character retain facts about a specific player across separate sessions. In the Convai Unreal Engine plugin, memory works when the character has LTM enabled and the chatbot sends a stable `EndUserID` at connect time.


How long-term memory works Understand what LTM stores, how player identity scopes memory, and what your project must persist between sessions.	/pages/Bc8OjnguS3F6H3oW7CJi
Long-term memory quick start Enable memory for one character, assign a stable player identity, and verify cross-session recall in Play In Editor.	/pages/qCWhjxGBv6qEO4Rkl0Ph
Configure memory for a character Enable or verify the character LTM setting and reset the local conversation link when needed.	/pages/F5FsqjGFVKgO3SLqnTYj
End-user identity Choose and assign a stable `EndUserID` before `StartSession` so memory stays scoped to the correct player.	/pages/qcfr1PrPOizoztRNloCY
Speaker ID management Create, list, and delete Speaker ID records through Blueprint nodes when your project uses the Speaker ID workflow.	/pages/xIpC6mQGKNJNnXc3TQWn
LTM Blueprint reference Reference for runtime `Convai\|LTM` Blueprint nodes, `FConvaiSpeakerInfo`, and the memory properties on both Convai components.	/pages/mwNxFe292Uo2iGpZiLAp
Long-term memory usage examples Blueprint-first patterns for returning learners, shared devices, account-backed identity, and fresh-start resets.	/pages/tyOWumFxG4lNGELvqAOH
Troubleshoot long-term memory Diagnose disabled memory, identity mismatches, Speaker ID failures, and sessions that start fresh.	/pages/rHYMia3zb5OAQe1S06cT

### Next steps Start with [How long-term memory works](/api-docs/plugins-and-integrations/convai-unreal-engine-plugin/features/long-term-memory/how-long-term-memory-works.md) for the mental model, then follow [Long-term memory quick start](/api-docs/plugins-and-integrations/convai-unreal-engine-plugin/features/long-term-memory/long-term-memory-quick-start.md) to get memory running in your level. {% content-ref url="/pages/Bc8OjnguS3F6H3oW7CJi" %} [How long-term memory works](/api-docs/plugins-and-integrations/convai-unreal-engine-plugin/features/long-term-memory/how-long-term-memory-works.md) {% endcontent-ref %} {% content-ref url="/pages/qCWhjxGBv6qEO4Rkl0Ph" %} [Long-term memory quick start](/api-docs/plugins-and-integrations/convai-unreal-engine-plugin/features/long-term-memory/long-term-memory-quick-start.md) {% endcontent-ref %} --- # 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/plugins-and-integrations/convai-unreal-engine-plugin/features/long-term-memory.md?ask=&goal= ``` `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.