---
title: "How Supermemory Works"
description: "Understanding the knowledge graph architecture that powers intelligent memory"
icon: "brain"
---
Supermemory isn't just another document storage system. It's designed to mirror how human memory actually works - forming connections, evolving over time, and generating insights from accumulated knowledge.
## The Mental Model
Traditional systems store files. Supermemory creates a living knowledge graph.
- Static files in folders
- No connections between content
- Search matches keywords
- Information stays frozen
- Dynamic knowledge graph
- Rich relationships between memories
- Semantic understanding
- Information evolves and connects
## Documents vs Memories
Understanding this distinction is crucial to using Supermemory effectively.
### Documents: Your Raw Input
Documents are what you provide - the raw materials:
- PDF files you upload
- Web pages you save
- Text you paste
- Images with text
- Videos to transcribe
Think of documents as books you hand to Supermemory.
### Memories: Intelligent Knowledge Units
Memories are what Supermemory creates - the understanding:
- Semantic chunks with meaning
- Embedded for similarity search
- Connected through relationships
- Dynamically updated over time
Think of memories as the insights and connections your brain makes after reading those books.
**Key Insight**: When you upload a 50-page PDF, Supermemory doesn't just store it. It breaks it into hundreds of interconnected memories, each understanding its context and relationships to your other knowledge.
## Memory Relationships
The graph connects memories through three types of relationships:
### Updates: Information Changes
When new information contradicts or updates existing knowledge, Supermemory creates an "update" relationship.
```text Original Memory
"You work at Supermemory as a content engineer"
```
```text New Memory (Updates Original)
"You now work at Supermemory as the CMO"
```
The system tracks which memory is latest with an `isLatest` field, ensuring searches return current information.
### Extends: Information Enriches
When new information adds to existing knowledge without replacing it, Supermemory creates an "extends" relationship.
Continuing our "working at supermemory" analogy, a memory about what you work on would extend the memory about your role given above.
```text Original Memory
"You work at Supermemory as the CMO"
```
```text New Memory (Extension) - Separate From Previous
"Your work consists of ensuring the docs are up to date, making marketing campaigns, SEO, etc."
```
Both memories remain valid and searchable, providing richer context.
### Derives: Information Infers
The most sophisticated relationship - when Supermemory infers new connections from patterns in your knowledge.
```text Memory 1
"Dhravya is the founder of Supermemory"
```
```text Memory 2
"Dhravya frequently discusses AI and machine learning innovations"
```
```text Derived Memory
"Supermemory is likely an AI-focused company"
```
These inferences help surface insights you might not have explicitly stated.
## Processing Pipeline
Understanding the pipeline helps you optimize your usage:
| Stage | What Happens |
|-------|-------------|
| **Queued** | Document waiting to process
| **Extracting** | Content being extracted |
| **Chunking** | Creating memory chunks |
| **Embedding** | Generating vectors |
| **Indexing** | Building relationships |
| **Done** | Fully searchable |
**Tip**: Larger documents and videos take longer. A 100-page PDF might take 1-2 minutes, while a 1-hour video could take 5-10 minutes.
## Next Steps
Now that you understand how Supermemory works:
Start adding content to your knowledge graph
Learn to query your knowledge effectively