> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/Kismetkanceled/geniehelper/llms.txt
> Use this file to discover all available pages before exploring further.

# Quick Start

> Step-by-step guide to clone, install, configure, and start Genie Helper services

# Quick Start Guide

This guide will walk you through setting up Genie Helper on your VPS. The platform is designed to run on a self-hosted server with all services managed via PM2.

<Note>
  **Prerequisites:**

  * Ubuntu/Debian VPS with at least 8GB RAM
  * Node.js 18+ installed
  * Docker and Docker Compose installed
  * Redis server running
  * Nginx or similar reverse proxy
</Note>

## Installation Steps

<Steps>
  <Step title="Clone the Repository">
    Clone the Genie Helper source code to your server:

    ```bash theme={null}
    git clone <repository-url> agentx
    cd agentx
    ```
  </Step>

  <Step title="Install Dependencies">
    Install Node.js dependencies for all services:

    ```bash theme={null}
    # Install main server dependencies
    npm install

    # Install dashboard dependencies
    cd dashboard
    npm install
    cd ..

    # Install media worker dependencies
    cd media-worker
    npm install
    cd ..
    ```
  </Step>

  <Step title="Configure Environment Variables">
    Create a `.env` file in the project root with the required credentials:

    ```bash theme={null}
    # Credentials encryption key (base64 of 32 bytes)
    CREDENTIALS_ENC_KEY_B64=<your-base64-key>

    # Directus admin token
    DIRECTUS_ADMIN_TOKEN=<your-directus-token>

    # RBAC sync webhook secret
    RBAC_SYNC_WEBHOOK_SECRET=<your-webhook-secret>

    # AnythingLLM configuration
    SERVER_PORT=3001
    STORAGE_DIR=./storage

    # Directus configuration
    DIRECTUS_URL=http://localhost:8055

    # Ollama configuration
    OLLAMA_BASE_URL=http://localhost:11434
    ```

    <Warning>
      Generate a secure 32-byte key for `CREDENTIALS_ENC_KEY_B64`:

      ```bash theme={null}
      node -e "console.log(require('crypto').randomBytes(32).toString('base64'))"
      ```
    </Warning>
  </Step>

  <Step title="Configure MCP Servers">
    The MCP server configuration is located at `storage/plugins/anythingllm_mcp_servers.json`. It should auto-boot on startup via the patched `server/utils/boot/index.js`.

    Verify the three MCP servers are configured:

    * **Directus MCP** — `scripts/directus-mcp-server.mjs`
    * **Ollama MCP** — `scripts/ollama-mcp-server.mjs`
    * **Stagehand MCP** — `scripts/stagehand-mcp-server.mjs`
  </Step>

  <Step title="Install Ollama Models">
    Pull the required Ollama models for AI operations:

    ```bash theme={null}
    ollama pull dolphin3:8b-llama3.1-q4_K_M
    ollama pull dolphin-mistral:7b
    ollama pull qwen-2.5:latest
    ollama pull phi-3.5:latest
    ollama pull llama3.2:3b
    ollama pull bge-m3:latest
    ```

    <Note>
      The `scout-fast-tag:latest` model is a custom SmolLM model for taxonomy classification. You'll need to build this separately if using the taxonomy features.
    </Note>
  </Step>

  <Step title="Build the Dashboard">
    Build the React SPA for production:

    ```bash theme={null}
    cd dashboard
    npm run build
    cd ..
    ```

    The build output will be in `dashboard/dist/` and should be served by your web server.
  </Step>

  <Step title="Configure Nginx Reverse Proxy">
    Set up Nginx to proxy requests to the various services:

    ```nginx theme={null}
    # SPA fallback for React Router
    error_page 404 =200 /index.html;

    # Directus API proxy
    location /api/directus/ {
        proxy_pass http://127.0.0.1:8055/;
        proxy_set_header Host $host;
    }

    # AnythingLLM proxy (with WebSocket support)
    location /api/llm/ {
        proxy_pass http://127.0.0.1:3001/;
        proxy_http_version 1.1;
        proxy_set_header Upgrade "upgrade";
        proxy_set_header Connection "upgrade";
        proxy_set_header Host $host;
        proxy_read_timeout 86400;
    }
    ```

    <Warning>
      **Plesk Users:** If using Plesk, add these rules via **Domains → Apache & nginx Settings → Additional nginx directives**. NEVER add `location /` — Plesk generates it automatically.
    </Warning>
  </Step>

  <Step title="Start Services with PM2">
    Use PM2 to manage all services:

    ```bash theme={null}
    # Start AnythingLLM
    pm2 start npm --name "anything-llm" -- start

    # Start Directus CMS
    pm2 start npm --name "agentx-cms" --cwd ./cms -- start

    # Start Stagehand server
    pm2 start npm --name "stagehand-server" --cwd ./stagehand -- start

    # Start Dashboard (serve static files)
    pm2 start npx --name "genie-dashboard" -- serve dashboard/dist -l 3100

    # Start Media Worker
    pm2 start npm --name "media-worker" --cwd ./media-worker -- start

    # Start Document Collector
    pm2 start npm --name "anything-collector" -- run collector

    # Save PM2 process list
    pm2 save
    pm2 startup
    ```
  </Step>
</Steps>

## Verify Installation

Check that all services are running:

```bash theme={null}
pm2 status
```

You should see the following services:

| Service            | Port | Status |
| ------------------ | ---- | ------ |
| anything-llm       | 3001 | online |
| agentx-cms         | 8055 | online |
| stagehand-server   | 3002 | online |
| genie-dashboard    | 3100 | online |
| media-worker       | —    | online |
| anything-collector | —    | online |

## Access the Platform

<CardGroup cols={2}>
  <Card title="Creator Dashboard" icon="grid">
    Access the main dashboard at `https://yourdomain.com/app/`
  </Card>

  <Card title="Admin Panel" icon="shield">
    Access the admin panel at `https://yourdomain.com/admin`
  </Card>

  <Card title="Directus CMS" icon="database">
    Direct access at `http://localhost:8055/admin`
  </Card>

  <Card title="AnythingLLM" icon="robot">
    Direct access at `http://localhost:3001`
  </Card>
</CardGroup>

### Default Credentials

<Warning>
  Change these credentials before public launch!
</Warning>

| Service     | Email                                                           | Password       |
| ----------- | --------------------------------------------------------------- | -------------- |
| Directus    | [admin@geniehelper.com](mailto:admin@geniehelper.com)           | password       |
| AnythingLLM | [poweradmin@geniehelper.com](mailto:poweradmin@geniehelper.com) | (MY)P@\$\$w3rd |

**AnythingLLM API Key:** `38KEHYS-NVPMBSX-GVVJNYH-VQHAN9S`

## Common Operations

### Restart All Services

```bash theme={null}
pm2 restart all
```

### Rebuild Dashboard After Code Changes

```bash theme={null}
cd dashboard && npm run build
```

### Restart AnythingLLM After Server Changes

```bash theme={null}
pm2 restart anything-llm
```

### View Service Logs

```bash theme={null}
# View AnythingLLM logs
pm2 logs anything-llm --lines 50

# View Media Worker logs
pm2 logs media-worker --lines 50

# View all logs
pm2 logs
```

### Monitor Service Status

```bash theme={null}
# Real-time monitoring
pm2 monit

# Service metrics
pm2 status
```

## Troubleshooting

<Accordion title="Services won't start">
  Check the logs with `pm2 logs <service-name>` to identify the error. Common issues:

  * Missing environment variables in `.env`
  * Port conflicts (check if ports 3001, 8055, 3002, 3100 are available)
  * Redis not running (required for BullMQ)
</Accordion>

<Accordion title="MCP servers not loading">
  Verify that `storage/plugins/anythingllm_mcp_servers.json` exists and contains valid JSON. Check AnythingLLM logs for MCP boot messages.
</Accordion>

<Accordion title="Nginx 502 errors">
  Ensure all upstream services are running:

  ```bash theme={null}
  curl http://localhost:3001  # AnythingLLM
  curl http://localhost:8055  # Directus
  ```
</Accordion>

<Accordion title="Ollama models not responding">
  Verify Ollama is running:

  ```bash theme={null}
  ollama list
  curl http://localhost:11434/api/tags
  ```

  If models are missing, re-run `ollama pull` commands from Step 5.
</Accordion>

## Next Steps

Now that your services are running:

<Steps>
  <Step title="Review Architecture">
    Learn how services communicate in the [Architecture guide](/architecture)
  </Step>

  <Step title="Connect Platforms">
    Link your OnlyFans and other creator platforms via the dashboard
  </Step>

  <Step title="Configure AI Agent">
    Customize the AI workspace and system prompts in AnythingLLM
  </Step>
</Steps>