---
title: "Overview — What is Supermemory?"
sidebarTitle: "Overview"
description = "Add long-term memory to your LLMs with three integration paths: AI SDK, Memory API, or Memory Router."
---

Supermemory gives your LLMs long-term memory. Instead of stateless text generation, they recall the right facts from your files, chats, and tools, so responses stay consistent, contextual, and personal.


## How does it work? (at a glance)

![](/images/232.png)

- You send Supermemory text, files, and chats.
- Supermemory [intelligently indexes them](/how-it-works) and builds a semantic understanding graph on top of an entity (e.g., a user, a document, a project, an organization).
- At query time, we fetch only the most relevant context and pass it to your models.

We offer three ways to add memory to your LLMs:

### Memory API — full control

- Ingest text, files, and chats (supports multi-modal); search & filter; re-rank results.
- Modelled after the actual human brain's working with smart forgetting, decay, recency bias, context rewriting, etc.
- API + SDKs for Node & Python; designed to scale in production.

<Info>
    You can reference the full API documentation for the Memory API [here](/api-reference/manage-memories/add-memory).
</Info>

### AI SDK

- Native Vercel AI SDK integration with `@supermemory/tools/ai-sdk`
- Memory tools for agents or infinite chat for automatic context
- Works with streamText, generateText, and all AI SDK features

```typescript
import { streamText } from "ai"
import { supermemoryTools } from "@supermemory/tools/ai-sdk"

const result = await streamText({
  model: anthropic("claude-3"),
  tools: supermemoryTools("YOUR_KEY")
})
```

<Info>
The AI SDK is recommended for new projects using Vercel AI SDK. The Router works best for existing **chat applications**, whereas the Memory API works as a **complete memory database** with granular control.
</Info>


### Memory Router — drop-in proxy with minimal code

- Keep your existing LLM client; just append `api.supermemory.ai/v3/` to your base URL.
- Automatic chunking and token management that fits your context window.
- Adds minimal latency on top of existing LLM requests.

<Note>
All three approaches share the **same memory pool** when using the same user ID. You can mix and match based on your needs.
</Note>

## Next steps

Head to the [**Router vs API**](/routervsapi) guide to understand the technical differences between the two and pick what’s best for you with a simple 4-question flow.