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

# Deployment

> Install, update, and configure Sinas

## Prerequisites

* A VPS or server with 2+ CPU cores, 4GB+ RAM, 50GB+ storage
* A domain name pointed at the server (A record)
* An SMTP service for login emails (SendGrid, Mailgun, AWS SES, etc.) — only required if you choose `otp` or `password+otp` auth mode. Skip for `password`-only / airgapped installs.

## Install

```bash theme={null}
sudo curl -fsSL https://raw.githubusercontent.com/sinas-platform/sinas/main/install.sh -o /tmp/sinas-install.sh && sudo bash /tmp/sinas-install.sh
```

The installer will:

* Install Docker if needed
* Generate secure keys (`SECRET_KEY`, `ENCRYPTION_KEY`, `DATABASE_PASSWORD`)
* Prompt for your domain, admin email, and authentication mode (and SMTP and/or admin password depending on the mode you pick)
* Create `.env` in `/opt/sinas/`
* Pull pre-built images from the container registry and start all services
* Caddy automatically provisions SSL via Let's Encrypt

All services start automatically: PostgreSQL, PgBouncer, Redis, ClickHouse, the backend API (port 8000), queue workers, the scheduler, and the web console (port 51245). Migrations run automatically on startup.

## Update

```bash theme={null}
cd /opt/sinas
docker compose pull
docker compose up -d
```

## Manual development installation

For local development, see [INSTALL.md](https://github.com/sinas-platform/sinas/blob/main/INSTALL.md).

## Log in

1. Open the console at `https://yourdomain.com:51245`
2. Enter your `SUPERADMIN_EMAIL` address
3. Then, depending on your `AUTH_MODE`:
   * `otp` — check your inbox for the 6-digit code
   * `password` — enter your `SUPERADMIN_PASSWORD`
   * `password+otp` — enter your password, then the emailed code
4. You're in. See [Authentication](/platform/authentication) for the full reference.

## Configure an LLM provider

Before agents can work, you need at least one LLM provider:

```bash theme={null}
curl -X POST https://yourdomain.com/api/v1/llm-providers \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "openai",
    "provider_type": "openai",
    "api_key": "sk-...",
    "default_model": "gpt-4o",
    "is_default": true
  }'
```

## Start chatting

A default agent is created on startup. Create a chat and send a message:

```bash theme={null}
# Create a chat with the default agent
curl -X POST https://yourdomain.com/agents/default/default/chats \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{}'

# Send a message (use the chat_id from the response)
curl -X POST https://yourdomain.com/chats/{chat_id}/messages/stream \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"content": "Hello!"}'
```

***