> ## Documentation Index
> Fetch the complete documentation index at: https://docs.sense-lab.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Self-Hosted Installation

> Install SenseLab locally with pip, npm, or Docker.

<Note>
  Using the managed platform? You don't need to install anything — see [Connect to SenseLab](/amfs/getting-started/saas-connection).
</Note>

This guide is for running SenseLab on your own infrastructure.

## Python SDK

```bash theme={null}
pip install amfs
```

<Note>Requires Python 3.11+.</Note>

Optional packages:

```bash theme={null}
pip install amfs-adapter-postgres   # Postgres adapter (full-text + vector search)
pip install amfs-adapter-s3         # S3-compatible adapter
pip install amfs-http-server        # HTTP/REST API server
pip install amfs-cli                # CLI tools
pip install amfs-mcp-server         # MCP server
```

### TypeScript SDK

```bash theme={null}
npm install @senselab-ai/amfs
```

### Docker

```bash theme={null}
docker run -p 8080:8080 -v amfs-data:/data ghcr.io/raia-live/amfs
```

See the [Docker & Kubernetes guide](/amfs/guides/docker) for Postgres, Helm, and production setup.

### Verify

```python theme={null}
from amfs import AgentMemory

mem = AgentMemory(agent_id="test")
entry = mem.write("test", "hello", "world")
print(entry.value)  # "world"
```

***

## Next Steps

<CardGroup cols={2}>
  <Card title="Quick Start" icon="rocket" href="/amfs/getting-started/quickstart">Write, read, and search memory.</Card>
  <Card title="MCP Setup" icon="plug" href="/amfs/guides/mcp">Connect your IDE to SenseLab.</Card>
  <Card title="Core Concepts" icon="brain" href="/amfs/concepts/overview">How SenseLab works under the hood.</Card>
  <Card title="Configuration" icon="gear" href="/amfs/getting-started/configuration">YAML config, adapters, and env vars.</Card>
</CardGroup>