supermemory/apps/docs/memory-api/overview.mdx
2025-09-28 16:42:06 -07:00

162 lines
3.5 KiB
Text

---
title: "Quickstart - 5 mins"
description: "Learn how to integrate supermemory into your application"
---
## Authentication
Head to [supermemory's Developer Platform](https://console.supermemory.ai) built to help you monitor and manage every aspect of the API.
All API requests require authentication using an API key. Include your API key as follows:
<CodeGroup>
```bash cURL
Authorization: Bearer YOUR_API_KEY
```
```typescript Typescript
// npm install supermemory
const client = new supermemory({
apiKey: "YOUR_API_KEY",
});
```
```python Python
# pip install supermemory
client = supermemory(
api_key="YOUR_API_KEY",
)
```
</CodeGroup>
## Installing the clients
You can use supermemory through the APIs, or using our SDKs
<CodeGroup>
```bash cURL
https://api.supermemory.ai/v3
```
```bash Typescript
npm i supermemory
```
```bash Python
pip install supermemory
```
</CodeGroup>
## Add your first memory
<CodeGroup>
```bash cURL
curl https://api.supermemory.ai/v3/documents \
--request POST \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer SUPERMEMORY_API_KEY' \
-d '{"content": "This is the content of my first memory."}'
```
```typescript Typescript
await client.memory.add({
content: "This is the content of my first memory.",
});
```
```python Python
client.memory.add(
content="This is the content of my first memory.",
)
```
</CodeGroup>
This will add a new memory to your supermemory account.
Try it out in the [API Playground](/api-reference/manage-memories/add-memory).
## Content Processing
<Accordion title="Processing steps" icon="sparkles">
When you add content to supermemory, it goes through several processing steps:
1. **Queued**: Initial state when content is submitted
2. **Extracting**: Content is being extracted from the source
3. **Chunking**: Content is being split into semantic chunks
4. **Embedding**: Generating vector embeddings for search
5. **Indexing**: Adding content to the search index
6. **Done**: Processing complete
</Accordion>
<Accordion title="Advanced Chunking" icon="sparkles">
The system uses advanced NLP techniques for optimal chunking:
- Sentence-level splitting for natural boundaries
- Context preservation with overlapping chunks
- Smart handling of long content
- Semantic coherence optimization
</Accordion>
## Search your memories
<CodeGroup>
```bash cURL
curl https://api.supermemory.ai/v3/search \
--request POST \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer SUPERMEMORY_API_KEY' \
-d '{"q": "This is the content of my first memory."}'
```
```typescript Typescript
await client.search.execute({
q: "This is the content of my first memory.",
});
```
```python Python
client.search.execute(
q="This is the content of my first memory.",
)
```
</CodeGroup>
Try it out in the [API Playground](/api-reference/search-memories/search-memories).
You can do a lot more with supermemory, and we will walk through everything you need to.
Next, explore the features available in supermemory
<CardGroup cols={2}>
<Card title="Adding memories" icon="plus" href="/memory-api/creation">
Adding memories
</Card>
<Card
title="Searching and filtering"
icon="search"
href="/memory-api/searching"
>
Searching for items
</Card>
<Card
title="Connectors and Syncing"
icon="plug"
href="/memory-api/connectors"
>
Connecting external sources
</Card>
<Card title="Features" icon="sparkles" href="/memory-api/features">
Explore Features
</Card>
</CardGroup>