> ## 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.

# Installation

> Install RightNow AI and set up your CUDA development environment

**RightNow AI** is an AI-powered CUDA code editor with real-time GPU profiling. Write optimized CUDA code with AI assistance and profile kernels without leaving your editor.

## System Requirements

<CardGroup cols={2}>
  <Card title="Windows" icon="windows">
    CUDA Toolkit 11.0-12.5 required
  </Card>

  <Card title="Linux" icon="linux">
    CUDA Toolkit 11.0-12.5 required
  </Card>
</CardGroup>

<Warning>
  **macOS**: Coming soon with serverless profiling
</Warning>

## Key Features

<CardGroup cols={2}>
  <Card title="Hardware-Aware AI Coding" icon="brain">
    **Smart CUDA Intelligence**

    * Context-aware autocomplete for GPU kernels
    * Ctrl+K editing with architecture-specific suggestions
    * Chat assistant trained on CUDA optimization patterns
    * Hardware-aware code generation (Ampere, Ada Lovelace, Hopper)
  </Card>

  <Card title="Real-Time GPU Profiling" icon="chart-line">
    **Production NCU Integration**

    * Live performance metrics as you code
    * 13+ hardware metrics (SM efficiency, memory bandwidth, occupancy)
    * Color-coded performance indicators (🟢 🟡 🔴)
    * One-click kernel profiling with ▶️ gutter buttons
  </Card>

  <Card title="Personalized AI Guidelines" icon="user-cog">
    **.rightnowrules Automation**

    * Auto-generated guidelines based on your GPU architecture
    * Personalized optimization recommendations
    * Project-specific CUDA development rules
    * Seamless integration with all AI features
  </Card>

  <Card title="Privacy-First AI Access" icon="shield-halved">
    **Flexible Provider Options**

    * OpenRouter BYOK with 200+ models
    * Local models (Ollama, vLLM, LM Studio)
    * Complete offline capability
    * Your code never leaves your machine with local providers
  </Card>

  <Card title="Profiling Data Persistence" icon="database">
    **Optimization History Tracking**

    * Persistent profiling data across sessions
    * Performance timeline and trend analysis
    * Content-based kernel identification
    * Team-shareable optimization insights
  </Card>

  <Card title="Zero-Friction CUDA Development" icon="rocket">
    **Get Productive Instantly**

    * Auto-detects your GPU and CUDA setup
    * No configuration needed - just install and code
    * Works with existing CUDA projects immediately
    * Intelligent error messages with actionable fixes
  </Card>
</CardGroup>

## Get Started

<Card title="Quick Start Guide" icon="rocket" href="/quickstart" horizontal>
  Get productive with CUDA development in 3 simple steps.
</Card>

<CardGroup cols={3}>
  <Card title="Core Features" icon="microchip" href="/core-features">
    AI coding, real-time profiling, and hardware integration
  </Card>

  <Card title="Advanced Features" icon="sparkles" href="/advanced-features">
    .rightnowrules personalization and profiling persistence
  </Card>

  <Card title="Configuration" icon="gear" href="/ai-providers">
    OpenRouter setup, CUDA profiling, and editor preferences
  </Card>
</CardGroup>