# Memory

The Memory plugin allows BoltAI to remember details between chats.

Once enabled, BoltAI will automatically remember details between chats. You can also explicitly tell BoltAI to remember certain information.

### How to set up the Memory plugin?

No configuration is required for this plugin.

### How to use the Memory Plugin?

1. Start a new chat. Choose an LLM that supports Function Calling (for example GPT-4o)
2. Enable the Memory plugin
3. Continue to use BoltAI as usual. It would automatically remember relevant information. You can also tell BoltAI to remember specific details.

{% hint style="info" %}
**NOTICE**:

* All memories are stored locally
* If enabled, memory content are added to the System Instruction on every request
* Temporary Chat does not use or create memories
  {% endhint %}

### How to view and manage memories

Go to **Settings > Plugins > Memory**. Choose tab `Memories`

<figure><img src="https://3493584844-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FynYW2xZqA52spY7XgWis%2Fuploads%2Fe1GKkDzssAhLr3okpbZq%2FCleanShot%202024-08-07%20at%2012.06.26%402x.png?alt=media&#x26;token=631c10a2-9cc2-4289-bb4d-562bb38a5e69" alt=""><figcaption><p>Manage Memory</p></figcaption></figure>

### Demo Video

{% embed url="<https://www.youtube.com/watch?v=CxeEfEa9Vik>" %}
BoltAI Memory Plugin
{% endembed %}


---

# Agent Instructions: 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.boltai.com/docs/plugins/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.