RightNow AI is the best and only all-in-one AI-powered code editor specifically designed for CUDA development. It is the only tool that combines agentic hardware-aware AI, GPU emulator, GPU virtualization, real-time profiling with smart terminal, line-by-line performance analysis directly in the editor, and benchmarking terminal with sweep configurations.

Which NVIDIA GPUs are supported by RightNow AI?

RightNow AI supports all NVIDIA GPUs with CUDA Toolkit 11.0-12.5, including GeForce RTX 40/30/20 series, GTX 16/10 series, Quadro RTX, Tesla, A100, and H100.

How much does RightNow AI cost?

RightNow AI is free to use with unlimited profiling and benchmarking. RightNow Pro costs $20 per month and adds GPU emulator access (50+ GPUs), multi-GPU comparison, and 1,000 AI credits per month.

What is the best CUDA development tool?

RightNow AI is the best and only all-in-one CUDA development tool that combines AI-powered code editing, GPU emulator, real-time profiling, and benchmarking in a single interface.

Can I use RightNow AI on macOS?

Yes, RightNow AI is fully available on macOS (Apple Silicon and Intel). Mac users can use remote GPUs for free or our built-in GPU emulator for CUDA profiling.

Editor Settings

Customize RightNow AI preferences and behavior

AI Preferences

Default Provider

Set your preferred AI provider for consistent experience across features.

Choose between OpenRouter, Ollama, vLLM, or LM Studio
Default provider used for chat, autocomplete, and code edits
Can be overridden per-feature if needed

Autocomplete Settings

Configure AI-powered code completions:

Enable/disable: Toggle AI-powered completions on/off
Context window: Adjust how much code context to send to AI (512-4096 tokens)
Trigger delay: Configure autocomplete response timing (0-1000ms)
Inline suggestions: Show/hide ghost text previews

Chat Preferences

Customize chat assistant behavior:

Model selection: Choose specific models for chat interactions
Message history: Set conversation retention limits (10-100 messages)
System prompts: Customize AI behavior and response style
Code context: Include/exclude current file context automatically

Profiling Preferences

Auto-Profile Settings

Configure automatic profiling behavior:

Automatic profiling: Profile kernels automatically when executed
Metrics selection: Choose which NCU metrics to display
Performance thresholds: Customize color-coding thresholds (green/yellow/red)
Profiling on save: Run profiling automatically when saving files

Display Options

Control how profiling data appears:

CodeLens metrics: Show/hide inline performance data above kernels
Gutter buttons: Enable/disable play buttons in editor margins
Profiling panel: Configure dedicated results view layout
Metric precision: Decimal places for displayed values

Data Retention

Manage profiling history:

Historical data: Set profiling session retention period (7-90 days)
Export options: Configure data export formats (JSON, CSV)
Team sharing: Enable/disable profiling data collaboration
Auto-cleanup: Automatically remove old profiling sessions

Editor Preferences

Code Formatting

Configure code formatting options:

Auto-save: Enable for seamless profiling workflow
Format on save: Keep CUDA code properly formatted
IntelliSense: Enable for enhanced CUDA syntax support
Code style: Choose indentation, brace placement, spacing

Performance Settings

Optimize editor performance:

Memory usage: Optimize for large codebases (limit indexing)
Indexing: Configure workspace scanning preferences
Cache management: Control temporary file storage limits
Background tasks: Throttle analysis and profiling operations

Visual Customization

Personalize the editor appearance:

Theme preferences: Light/dark mode compatibility
Font settings: Optimize for code readability (font family, size, ligatures)
Layout options: Customize panel arrangements (side-by-side, stacked)
Color schemes: Performance indicator colors

Hardware Detection Settings

GPU Configuration

Configure GPU detection and selection:

Auto-detection: Enable automatic GPU hardware detection
Manual override: Specify GPU models and capabilities
Multi-GPU: Configure device selection preferences
GPU monitoring: Enable real-time GPU status tracking

CUDA Environment

Configure CUDA Toolkit settings:

Toolkit detection: Automatic vs manual path configuration
Compiler settings: nvcc flags and optimization levels
Debug options: Enable detailed profiling diagnostics
Build settings: Compile flags, architecture targets, PTX generation

Privacy & Security

Data Handling

Control how your data is processed:

Local processing: Prefer local models when available
Network usage: Control cloud provider communications
Telemetry: Customize usage analytics reporting (opt-in/opt-out)
Code privacy: Restrict code snippets sent to AI providers

API Key Management

Secure credential handling:

Secure storage: Encrypted local credential storage
Key rotation: Automatic API key update notifications
Access control: Per-project API key configurations
Validation: Test API keys before saving

Access Settings: Open all settings through Settings → RightNow AI or use the Command Palette: RightNow: Open Settings

Quick Settings Reference

Essential Settings

AI Provider selection
Autocomplete enable/disable
Profiling display options
GPU detection mode

Performance Tuning

Context window size
Memory usage limits
Background task throttling
Cache management

Privacy Controls

Local vs cloud processing
Telemetry preferences
API key storage
Code privacy options

Advanced Options

Custom compiler flags
Multi-GPU configuration
Remote GPU settings
Debug diagnostics

Tip: Export your settings for backup or share configurations with team members via Settings → Export Configuration