> For the complete documentation index, see [llms.txt](https://docs.zus.network/zus-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.zus.network/zus-docs/webapps/vult/vult-ai/memory-retention.md).

# Memory Retention

Vult AI incorporates memory retention to enhance user interactions by allowing AI to remember past conversations and user preferences. This feature ensures a more context-aware experience by maintaining a record of previous discussions, user queries, and attached files.

Vult AI uses Mem0 AI, a dedicated memory storage API, to handle user memory. This enables the AI to recall details from previous interactions, making conversations smarter and more personalized over time.

### **How Memory Retention Works**

<figure><img src="/files/YjoWN29cuJcTYYxJN08U" alt=""><figcaption></figcaption></figure>

#### **1. Memory Storage with Mem0 AI**

* Every AI interaction in Vult AI Chat is stored using Mem0 AI, which acts as a retrieval-based memory system.
* The AI retains important details such as:
  * User queries.
  * AI-generated responses.
  * Any relevant metadata like timestamps

#### **2. Memory Retrieval in Conversations**

* When a user asks a follow-up question, Vult AI **searches the stored memory** for relevant past conversations.
* If a match is found, the AI retrieves previous responses and **contextually enhances the new response**.
* Example:
  * User: *"My name is Jack."*
  * AI: *"Nice to meet you, Jack."*
  * User (later): *"What’s my name?"*
  * AI: *"Your name is Jack."*

#### **3. Memory Integration in AI Chat and AI Agent**

* **AI Chat:**. Unlike traditional AI platforms, VultAI does not store any conversation data on its servers. Instead, when you interact with AI Chat, any essential information is temporarily captured to support more natural, continuous conversations. This session history is stored securely on your own allocation within the Züs decentralized storage network. It does **not** maintain context across different files.
* **AI Agent:** Uses stored memory **only within a single processing request** and does **not** maintain context across different files.
* **Batch Processing:** Does not leverage memory retention, as each file is processed independently.

### **Session-Based Memory vs Long-Term Memory**

<table><thead><tr><th>Feature</th><th width="171">AI Chat (Home)</th><th>AI Agent (All Files)</th><th>Batch Processing</th></tr></thead><tbody><tr><td><strong>Memory Retention</strong></td><td>Yes, via Mem0 AI</td><td>Yes, Via Mem0 AI</td><td>No, processes each request independently</td></tr><tr><td><strong>Stored Interactions</strong></td><td>Yes, saved in AI Chat Folder</td><td>Yes, saved in AI Agent Folder</td><td>Batch Folder Within AI Agent</td></tr><tr><td><strong>Contextual Awareness</strong></td><td>Yes, recalls previous prompts</td><td>No, processes only current file</td><td>No contextual linking</td></tr></tbody></table>

### **Benefits of Memory Retention in Vult AI**

#### **1. Personalized AI Conversations**

* The AI remembers **important user details** (e.g., name, project details, or past requests).
* Follow-up questions feel **more natural**, as the AI recalls previous responses.

#### **2. Faster and More Relevant Responses**

* Instead of **repeating context**, users can **build upon past interactions**, improving efficiency.
* AI can reference previous discussions instead of starting from scratch.

***

### **Limitations of Memory Retention**

#### **1. Limited to AI Chat Only**

* The AI retains memory **only in conversations** and does **not** remember previous file-based AI Agent interactions.

#### **2. No Cross-Session Memory Sharing**

* If a user starts a **new chat session**, past memory is **not carried over** unless explicitly recalled.

#### **3. File Attachments Are Not Memorized**

* While the AI can process attached files, it **does not** store the file itself in memory.
* Users must **re-upload** the file in future sessions if they want the AI to reference it again.


---

# 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.zus.network/zus-docs/webapps/vult/vult-ai/memory-retention.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.