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

# Quickstart

> Get up and running with MINDBLIX in under 5 minutes. This guide walks you through installation, setup, and deploying your first AI agent.

## Prerequisites

Before you begin, make sure you have the following installed:

> **Python 3.10+**
>
> Required for backend agent runtime

> **Node.js 18+**
>
> Required for dashboard and CLI tools

You'll also need:

* A MINDBLIX account ([sign up here](https://mindblix.com))
* An API key (available from your dashboard)

***

## Step 1: Clone the Repository

```bash theme={null}
git clone https://github.com/Dolphin-Syndrom/Multi-AI-Agent-System.git
cd Multi-AI-Agent-System
```

## Step 2: Set Up the Backend

**1. Navigate to Backend**

```bash theme={null}
cd backend
```

**2. Install Dependencies**

We use [uv](https://docs.astral.sh/uv/) for fast Python dependency management:

```bash theme={null}
pip install uv
uv sync
```

**3. Configure Environment**

Copy the example environment file and add your API keys:

```bash theme={null}
cp .env.example .env
```

Edit `.env` with your configuration:

```env theme={null}
GEMINI_API_KEY=your_gemini_api_key
DATABASE_URL=your_database_url
JWT_SECRET=your_jwt_secret
```

**4. Start the Server**

```bash theme={null}
uv run uvicorn app.main:app --reload --port 8000
```

> [!TIP]
>
> You should see: `Uvicorn running on http://127.0.0.1:8000`

## Step 3: Set Up the Dashboard

**1. Navigate to Dashboard**

```bash theme={null}
cd ../frontend-dashboard
```

**2. Install Dependencies**

```bash theme={null}
npm install
```

**3. Start the Dashboard**

```bash theme={null}
npm run dev
```

> [!TIP]
>
> Dashboard available at `http://localhost:3000`

## Step 4: Deploy Your First Agent

Once both backend and dashboard are running, you can deploy your first agent:

**Via Dashboard**

1. Open `http://localhost:3000` in your browser
2. Navigate to **Agents** → **Create New**
3. Select a template (e.g., *Research Agent*)
4. Configure the agent parameters
5. Click **Deploy**

**Via API**

```bash theme={null}
curl -X POST http://localhost:8000/api/v1/agents \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "My Research Agent",
    "template": "research",
    "config": {
      "model": "gemini-1.5-flash",
      "max_iterations": 5
    }
  }'
```

**Via Python SDK**

```python theme={null}
from mindblix import MindBlix

client = MindBlix(api_key="YOUR_API_KEY")

agent = client.agents.create(
    name="My Research Agent",
    template="research",
    config={
        "model": "gemini-1.5-flash",
        "max_iterations": 5
    }
)

print(f"Agent deployed: {agent.id}")
```

***

## What's Next?

> **[Architecture Overview](https://docs.mindblix.tech/architecture.md)**
>
> Deep dive into how MINDBLIX works under the hood.

> **[Core Concepts](https://docs.mindblix.tech/concepts/agents.md)**
>
> Learn about agents, workflows, and orchestration patterns.

> **[Create Custom Agents](https://docs.mindblix.tech/guides/creating-agents.md)**
>
> Build your own specialized agents from scratch.

> **[API Reference](https://docs.mindblix.tech/api-reference/introduction.md)**
>
> Explore the full API documentation.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.