> For the complete documentation index, see [llms.txt](https://docs.zeroauthority.xyz/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.zeroauthority.xyz/nova-bot/nova-ai-agent/memory-and-personalization.md).

# Memory & Personalization

Nova remembers your conversations and can learn context-specific information about your server or group, making interactions faster and more relevant over time.

***

## How Memory Works

Nova uses a tiered memory system:

* **Recent context** — the last few messages in your conversation, for natural follow-ups
* **Short-term memory** — key topics from the last 48 hours, for continuity
* **Long-term memory** — important facts and summaries, stored for up to 30 days

Blockchain-related conversations are prioritized for longer retention.

***

## Teaching Nova

Ask Nova to remember specific facts about your server or group, and it will recall them in future conversations within the same context.

**Example prompt:**

> *"Remember that our project token is WELSH"* — later, ask *"what do you remember about our project?"*

***

## User Preferences

Personalize how Nova interacts with you — preferences follow you across all servers and groups where Nova is active.

**Example prompt:**

> *"Set my timezone to UTC-5"*

**Available preferences:** timezone, response style (concise vs detailed), language preference, and personal notes.