---
title: "supermemory docs"
sidebarTitle: "Overview"
description: "The context engine for AI apps — memories, a knowledge graph, and live profiles from everything you feed it."
mode: "center"
icon: "book-open"
---

Supermemory is a context engine. You feed it everything — chat sessions, files, URLs, connector data — and it derives memories, a knowledge graph, and live profiles. When your app needs context, supermemory serves the right slice back in ~300ms. {/* CONFIRM: publishable latency figure */}

The whole loop is two calls:

<CodeGroup>

```typescript TypeScript
await client.add({
  content: "Sarah's being promoted to VP of Product",
  containerTag: "user_4f8a",
});

const results = await client.search.memories({
  q: "who's getting promoted?",
  containerTag: "user_4f8a",
});
```

```python Python
client.add(
    content="Sarah's being promoted to VP of Product",
    container_tag="user_4f8a",
)

results = client.search.memories(
    q="who's getting promoted?",
    container_tag="user_4f8a",
)
```

</CodeGroup>

## Start here

<Columns cols={2}>
  <Card title="Quickstart" icon="bolt" href="/quickstart">
    Add four scattered memories, then watch supermemory connect them into an answer you never stated.
  </Card>
  <Card title="How it works" icon="brain" href="/concepts/architecture">
    The custom memory model, the graph, and where the milliseconds go.
  </Card>
</Columns>

## Pick your door

Every surface below is a door into the same engine — one store of memories, one graph, one set of profiles. Anything that goes in through one door comes out through all of them.

<Columns cols={3}>
  <Card title="API & SDKs" icon="code" href="/concepts/surfaces">
    Full control from your own backend. TypeScript, Python, REST.
  </Card>
  <Card title="MCP" icon="terminal" href="/supermemory-mcp/mcp">
    Give Claude, Cursor, and ChatGPT your memory. No code.
  </Card>
  <Card title="Plugins" icon="puzzle" href="/integrations/claude-code">
    Auto-inject memory into Claude Code, Codex, and OpenClaw.
  </Card>
  <Card title="Connectors" icon="plug" href="/connectors/overview">
    Notion, Google Drive, Gmail, OneDrive, S3 — content flows in on its own.
  </Card>
  <Card title="SMFS" icon="database" href="/smfs/overview">
    Mount memory as a filesystem for agents that think in files.
  </Card>
  <Card title="Self-hosting" icon="server" href="/self-hosting/overview">
    From a free local binary to air-gapped enterprise deploys.
  </Card>
</Columns>

## Go deep

<Columns cols={2}>
  <Card title="Build on supermemory" icon="blocks" href="/patterns/overview">
    Multi-tenant SaaS memory, AI companions, multi-agent systems, company brains — full patterns with code.
  </Card>
  <Card title="API Reference" icon="book-open" href="/api-reference">
    Every endpoint, parameter, and response shape.
  </Card>
  <Card title="Permissioning & multi-tenancy" icon="lock" href="/concepts/permissioning">
    Container tags, metadata, scoped keys — real isolation, designed in.
  </Card>
  <Card title="Memory vs RAG" icon="scale" href="/concepts/memory-vs-rag">
    Why retrieval alone recommends Adidas to someone who switched to Puma two weeks ago.
  </Card>
</Columns>

## Why supermemory

Most "memory layers" are a vector store that retrieves the nearest chunk. Supermemory understands what it stores: facts carry time, entities connect across sessions, contradictions resolve to what's true *now*, and irrelevant details fade.

- **State of the art** on LongMemEval and LoCoMo — and [MemoryBench](/memorybench/overview) lets you reproduce the numbers yourself. {/* CONFIRM: exact benchmark figures + ConvoMem */}
- **Fast enough for the hot path**: profile reads ~100ms, search P50 ~300ms. {/* CONFIRM: publishable latency figures */}
- **Yours to run**: the same engine powers the cloud API, a free local binary, and on-prem enterprise deploys.