> ## Documentation Index
> Fetch the complete documentation index at: https://docs.praxis-ai.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Memory Systems

> Your digital twin uses three complementary memory systems to provide both immediate context and long-term personalization

Your digital twin uses three complementary memory systems. Understanding the difference helps you get consistent, personalized answers without paying for context you don't need.

<CardGroup cols={3}>
  <Card title="Conversation History" icon="clock" href="/mdx/user-guide/memory/conversation-history">
    Short-term context for the current conversation
  </Card>

  <Card title="User Memory" icon="brain" href="/mdx/user-guide/memory/user-memory">
    Long-term facts and preferences Pria remembers about you
  </Card>

  <Card title="Shared Memory" icon="users" href="/mdx/user-guide/memory/shared-memory">
    Knowledge shared with everyone using the same Digital Twin
  </Card>
</CardGroup>

***

## Conversation History — short-term context

Your digital twin's "working memory" for the current conversation: recent exchanges are included with each new prompt so it can follow what you're talking about.

* **Temporary** — only the current conversation; resets when you start a new one.
* **Adjustable** — the **Remember History** slider (sidebar → Knowledge) runs from **0 to 15** dialogues; default is 3.
* **Cost-aware** — more history = more tokens per request. At 6 or higher, smart compaction summarizes older exchanges automatically.

```markdown wrap theme={null}
You: "Let's work on API documentation for our payment system"
Twin: "Great! I'll help with your payment API docs."

[10 messages later...]

You: "Add the error codes section"
Twin: "I'll add error codes to the payment API documentation we've been building."
```

<Note>
  Full guide: [Conversation History](/mdx/user-guide/memory/conversation-history)
</Note>

***

## User Memory — long-term personalization

Persistent **memory parameters** (key/value facts with descriptions) Pria keeps about you: your role, preferences, projects, and style. Stored automatically when something important comes up, or explicitly when you say *"remember that…"*. You can view, edit, share, and delete every parameter from **My Profile → Memory**.

```markdown wrap theme={null}
Session 1: "I'm a technical writer at Acme Corp, and I prefer concise documentation"
[User Memory stores: Role=Technical Writer, Company=Acme Corp, Style=Concise]

Session 2 (weeks later): "Help me with new API docs"
Twin: "I'll create concise API documentation for Acme Corp, matching your preferred style."
```

<Note>
  Full guide: [User Memory](/mdx/user-guide/memory/user-memory)
</Note>

***

## Shared Memory — team knowledge

A Digital Twin's collective bulletin board: parameters shared with **every member** of the twin. Use it for team standards, policies, and reference information that should guide everyone's conversations. Shared entries record who added them; authors can always edit their own.

```markdown wrap theme={null}
User A: "Remember for the team: all pull requests require two approvals"

User B (days later): "How many approvals do I need for my pull request?"
Twin: "According to your team's guidelines, all pull requests require two approvals."
```

<Note>
  Full guide: [Shared Memory](/mdx/user-guide/memory/shared-memory)
</Note>

***

## Comparison

| Aspect           | Conversation History                | User Memory                   | Shared Memory                           |
| ---------------- | ----------------------------------- | ----------------------------- | --------------------------------------- |
| **Duration**     | Temporary (current conversation)    | Permanent                     | Permanent                               |
| **Who sees it**  | Only this conversation              | Only you                      | All members of the Digital Twin         |
| **Purpose**      | Conversation continuity             | Long-term personalization     | Collaborative knowledge sharing         |
| **Content**      | Complete recent exchanges           | Preferences, goals, decisions | Guidelines, standards, resources        |
| **Control**      | Remember History slider (0–15)      | Automatic + Memory panel      | Any member adds; authors edit their own |
| **Cost impact**  | Direct (more history = more tokens) | Minimal (compact parameters)  | Minimal (compact parameters)            |
| **Organization** | Chronological                       | Namespaced                    | Namespaced                              |

***

## Best practices

1. **Adjust history length** to the conversation — high for deep work, low for quick questions.
2. **Move durable facts into User Memory** — preferences stated once in memory beat re-explaining them in every chat.
3. **Use Shared Memory for team standards** — set them once, everyone benefits.
4. **Review periodically** — clear stale memory parameters and outdated shared entries so personalization stays accurate.