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

# Docker

> Get started with CORE in 5 minutes

> **Warning:**\
> You can self-host CORE on your own infrastructure using Docker.\
> The following instructions will use Docker Compose to spin up a CORE instance.\
> Make sure to read the [self-hosting overview](/self-hosting/overview) first.\
> As self-hosted deployments tend to have unique requirements and configurations, we don’t provide specific advice for securing your deployment, scaling up, or improving reliability.\
> **This guide alone is unlikely to result in a production-ready deployment. Security, scaling, and reliability concerns are not fully addressed here.**\
> Should the burden ever get too much, we’d be happy to see you on CORE Cloud where we deal with these concerns for you.

## Requirements

These are the minimum requirements for running the core.

### Prerequisites

To run CORE, you will need:

* Docker 20.10.0+
* Docker Compose 2.20.0+

### System Requirements

* 4+ vCPU
* 8+ GB RAM
* 20+ GB Storage

## Deployment Options

CORE offers multiple deployment approaches depending on your needs.

### Quick Deploy with Railway

For a one-click deployment experience, use Railway:

[![Deploy on Railway](https://railway.com/button.svg)](https://railway.com/deploy/core?referralCode=LHvbIb\&utm_medium=integration\&utm_source=template\&utm_campaign=generic)

Railway will automatically set up all required services and handle the infrastructure for you.

### Wizard with the CLI

If you have the CLI installed, the fastest path is:

```bash theme={null}
npm install -g @redplanethq/corebrain
corebrain setup
```

The wizard prompts for an install directory, an AI provider (OpenAI / Anthropic / Google / Ollama / Azure / OpenRouter / DeepSeek / Vercel / Groq / Mistral / xAI), the relevant API key, optional `OPENAI_BASE_URL` for OpenAI-compatible proxies, and a chat model. It auto-generates `SESSION_SECRET`, `ENCRYPTION_KEY`, `MAGIC_LINK_SECRET`, and the Neo4j password, fetches the canonical `docker-compose.yaml` + `.env.example` from `main`, applies your overrides, and runs `docker compose up -d`.

### Manual Docker Deployment

> **Prerequisites:**
> Before starting any deployment, ensure you have your `OPENAI_API_KEY` ready. This is required for AI functionality in CORE.
> If you use an OpenAI-compatible proxy, `OPENAI_API_KEY` can typically be any non-empty value, and you can also set `OPENAI_BASE_URL`.

### Combined Setup

For self deployment:

1. Clone core repository
   ```bash theme={null}
   # Clone the repository
   git clone https://github.com/RedPlanetHQ/core.git
   cd core/hosting/docker
   ```

2. Start the services:

   > **Using an OpenAI-compatible proxy and/or Ollama?**
   > CORE supports OpenAI-compatible proxies via `OPENAI_BASE_URL` and optional Ollama (chat and/or embeddings) via `OLLAMA_URL`.
   > Configure these in `.env`, then (optionally) uncomment the `ollama` service in `docker-compose.yaml`.
   > After changing env vars, restart the services for changes to take effect.

   ```bash theme={null}
   docker compose up -d
   ```

## Configuring Your Host URL

After deployment, set your public host URL so that Gateway and channel integrations (Slack, WhatsApp, etc.) can reach your instance.

In your `.env` file, update the following variables to match your actual host:

```env theme={null}
APP_ORIGIN=https://your-domain.com
LOGIN_ORIGIN=https://your-domain.com
```

* **`APP_ORIGIN`**: The public URL of your CORE instance. Used by the Gateway and channel integrations to construct callback and webhook URLs.
* **`LOGIN_ORIGIN`**: The URL used for authentication flows (magic links, OAuth redirects). Usually the same as `APP_ORIGIN`.

> If these are not set correctly, Gateway connections and channel webhooks (e.g. Slack events, WhatsApp callbacks) will fail to reach your instance.

## Next Steps

Once deployed, you can:

* Configure your AI providers (OpenAI, Anthropic, etc.)
* Set up integrations (Slack, GitHub, Gmail)
* Start building your memory graph
* Explore the CORE API and SDK