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

# Quick Start

> Get productive with CUDA development in 3 simple steps

## Get started in 3 steps

### Step 1: Installation

<AccordionGroup>
  <Accordion icon="download" title="Download RightNow AI">
    1. Visit [rightnowai.co](https://www.rightnowai.co) and download for your platform
    2. Run the installer and follow setup prompts
    3. Launch RightNow AI
  </Accordion>

  <Accordion icon="cube" title="Install CUDA Toolkit">
    **Required**: CUDA Toolkit 11.0-12.5

    1. Download from [NVIDIA Developer](https://developer.nvidia.com/cuda-toolkit)
    2. Install the toolkit for your platform (Windows/Linux)
    3. Verify installation: `nvcc --version`

    <Tip>RightNow AI will automatically detect your CUDA installation</Tip>
  </Accordion>
</AccordionGroup>

### Step 2: Open Your First CUDA Project

<AccordionGroup>
  <Accordion icon="folder" title="Create a new project">
    ```bash theme={null}
    # Create a new project folder
    mkdir my-cuda-project
    cd my-cuda-project

    # Open in RightNow AI
    rightnow .
    ```

    Or use **File → Open Folder** in the UI.
  </Accordion>

  <Accordion icon="code" title="Create your first CUDA file">
    Create a simple `hello.cu` file:

    ```cuda theme={null}
    #include <stdio.h>

    __global__ void hello() {
        printf("Hello from GPU thread %d!\n", threadIdx.x);
    }

    int main() {
        hello<<<1, 10>>>();
        cudaDeviceSynchronize();
        return 0;
    }
    ```
  </Accordion>
</AccordionGroup>

### Step 3: Enable AI & Profile

<AccordionGroup>
  <Accordion icon="key" title="Setup OpenRouter API Key (Free Tier)">
    **Required for AI features - OpenRouter is the only supported BYOK provider**

    1. Create account at [openrouter.ai](https://openrouter.ai)
    2. Get API key from [openrouter.ai/settings/keys](https://openrouter.ai/settings/keys)
    3. In RightNow AI: **Settings** → **AI Providers** → **OpenRouter**
    4. Enter your OpenRouter API key
    5. Test connection

    **Alternative**: Upgrade to [RightNow Pro](https://www.rightnowai.co/pricing) for managed AI access
  </Accordion>

  <Accordion icon="chart-line" title="Profile your first kernel">
    1. Click the **▶️ button** next to your `__global__` function
    2. View comprehensive metrics:
       * Execution time and SM efficiency
       * Memory throughput and occupancy
       * Cache hit rates and power consumption
    3. See color-coded performance indicators (🟢 🟡 🔴)
    4. Get AI-powered optimization suggestions

    <Tip>Try asking the AI: "How can I optimize this kernel for memory bandwidth?"</Tip>
  </Accordion>
</AccordionGroup>

## What's Next?

<CardGroup cols={2}>
  <Card title="AI-Powered Coding" icon="robot" href="/core-features">
    Use Ctrl+K editing and chat for CUDA development
  </Card>

  <Card title="Advanced Profiling" icon="chart-bar" href="/core-features">
    Explore comprehensive NCU metrics and AI optimization
  </Card>

  <Card title="Local Models" icon="server" href="/configuration">
    Set up Ollama, vLLM for privacy-first development
  </Card>

  <Card title="OpenRouter Models" icon="key" href="/configuration">
    Access 200+ models through OpenRouter integration
  </Card>
</CardGroup>

<Info>
  **Need help?** Try the chat sidebar and ask: "How do I get started with CUDA profiling?"
</Info>