Core Concepts
Understanding how Hebbrix thinks about memory will help you use it better. Don't worry - it's simpler than it sounds.
1. Memories
A "memory" is just a piece of information. It could be:
- A chat message ("User prefers dark mode")
- A document you uploaded (your company's FAQ)
- A preference ("Speaks Spanish")
- Literally anything you want the AI to remember
2. Collections
Collections are folders for organizing memories. Like:
customer-support- All support conversationsproduct-docs- Your documentationuser-preferences- Settings and choicesWhen searching, you can filter by collection to find specific types of memories faster.
3. The 3-Tier Memory System
Hebbrix mimics how human memory works with three layers:
Short-Term Memory (STM)
High priority, fades quickly
Recent stuff - like things from today or this week.
Example: "User asked about pricing 2 hours ago"
Medium-Term Memory (MTM)
Refreshed if accessed again
Things you remember for weeks or months.
Example: "User's name is John, prefers email communication"
Long-Term Memory (LTM)
Permanent knowledge
Important facts that should never be forgotten.
Example: "Our refund policy is 30 days", "John is a premium customer"
Hebbrix automatically manages these tiers using the Ebbinghaus Forgetting Curve - memories naturally decay over time unless they're accessed again, just like in real brains.
4. Knowledge Graph
Behind the scenes, Hebbrix builds a graph of how things connect. For example:
John → works_at → Acme Corp
John → prefers → email
Acme Corp → industry → SaaS
email → faster_than → phone_calls
This helps the AI understand relationships and make smarter connections. You don't need to manage this - it happens automatically.