Skip to main content

RightNow CLI - GPU-Native AI Code Editor for CUDA development

Project description

RightNow CLI - GPU-Native AI Code Editor

    ██████╗ ██╗ ██████╗ ██╗  ██╗████████╗███╗   ██╗ ██████╗ ██╗    ██╗
    ██╔══██╗██║██╔════╝ ██║  ██║╚══██╔══╝████╗  ██║██╔═══██╗██║    ██║
    ██████╔╝██║██║  ███╗███████║   ██║   ██╔██╗ ██║██║   ██║██║ █╗ ██║
    ██╔══██╗██║██║   ██║██╔══██║   ██║   ██║╚██╗██║██║   ██║██║███╗██║
    ██║  ██║██║╚██████╔╝██║  ██║   ██║   ██║ ╚████║╚██████╔╝╚███╔███╔╝
    ╚═╝  ╚═╝╚═╝ ╚═════╝ ╚═╝  ╚═╝   ╚═╝   ╚═╝  ╚═══╝ ╚═════╝  ╚══╝╚══╝

                    CUDA AI Assistant • Open Source

rightnowai.co@rightnowai_coDiscord

Version Python License

Open Source CLI Tool - Want a full-featured CUDA development environment with code completion, integrated debugging, and advanced AI features? Try RightNow Code Editor - Our complete IDE for GPU development.

RightNow CLI is an AI-powered CUDA development assistant that helps you write, optimize, and debug GPU code. Start FREE with no credit card required!

RightNow CLI Demo


Quick Install (30 seconds)

Option 1: pip (Recommended)

pip install rightnow-cli

Option 2: Quick Install Scripts

Linux/macOS:

curl -sSL https://raw.githubusercontent.com/RightNow-AI/rightnow-cli/main/install.sh | bash

Windows (PowerShell as Admin):

irm https://raw.githubusercontent.com/RightNow-AI/rightnow-cli/main/install.ps1 | iex

Getting Started (2 minutes)

1. Get your FREE API key (30 seconds)

# Visit OpenRouter (no credit card needed!)
https://openrouter.ai

# Sign up with Google/GitHub for instant access
# Copy your API key from the dashboard

2. Start RightNow

rightnow
# Paste your API key when prompted (one-time setup)

3. Start coding!

You: Create a vector addition CUDA kernel

RightNow: [Creates optimized kernel with detailed explanations]

What Can It Do?

For Beginners

  • Learn CUDA: "Explain how CUDA threads work"
  • Write Code: "Create a simple matrix multiplication kernel"
  • Fix Errors: "Help! My kernel crashes with error X"

For Experts

  • Optimize: "Optimize this kernel for memory coalescing"
  • Debug: "Find the race condition in my code"
  • Analyze: "Profile this kernel and suggest improvements"

Key Features

Start FREE

  • No credit card required
  • Free models included (Google Gemini, Meta Llama)
  • Upgrade to premium models when needed

Smart AI Agents

  • General Assistant: Helps with any CUDA task
  • Optimizer: Maximizes performance
  • Debugger: Finds and fixes bugs
  • Analyzer: Explains and improves code

Powerful Tools

  • Read and write CUDA files
  • Analyze performance bottlenecks
  • Generate optimized variants
  • Monitor GPU status
  • Execute bash commands

Example Usage

Basic Commands

# Start interactive mode
rightnow

# Inside RightNow:
/models     # List available AI models
/gpu        # Show GPU status
/clear      # Clear conversation
/help       # Show help
/quit       # Exit

Example Conversations

Creating a Kernel:

You: Create a parallel reduction kernel

RightNow: [Writes complete kernel with shared memory optimization]

Optimizing Code:

You: Optimize my matrix multiplication for RTX 4090

RightNow: [Analyzes and provides optimized version with 10x speedup]

Debugging:

You: My kernel gives wrong results for large arrays

RightNow: [Identifies overflow issue and provides fix]

Available Models

Free Models (No cost!)

  • Google Gemini 2.0 Flash - Fast and capable (default)
  • Meta Llama 3.2 3B - Efficient for simple tasks

Premium Models (Pay-per-use via OpenRouter)

  • GPT-4o - Most capable overall
  • Claude 3.5 Sonnet - Best for complex code
  • Gemini 1.5 Flash - Fast with huge context

Switch models anytime with /models command!

System Requirements

Minimum

  • Python 3.9+
  • Any OS (Windows, Linux, macOS)
  • Internet connection

Recommended (for CUDA features)

  • NVIDIA GPU (GTX 1650 or newer)
  • CUDA Toolkit 11.0+
  • 8GB+ RAM

Troubleshooting

"Command not found"

# Add to PATH (Linux/macOS)
export PATH="$HOME/.local/bin:$PATH"

# Or reinstall
pip uninstall rightnow-cli
pip install rightnow-cli --user

"API key error"

# Get your free key at:
https://openrouter.ai

# Clear old key and re-enter:
rm -rf ~/.rightnow-cli
rightnow  # Will prompt for new key

GPU not detected

# Check NVIDIA driver
nvidia-smi

# Check CUDA
nvcc --version

# RightNow works without GPU (CPU simulation mode)

Documentation

Contributing

We welcome contributions! Please see CONTRIBUTING.md for guidelines.

License

Proprietary Non-Commercial License - FREE for personal and educational use. See LICENSE for details.

For commercial use, contact: licensing@rightnowai.co

Support


Built with <3 by the RightNow AI Team
First GPU Native AI Code Editor

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

rightnow_cli-1.0.0.tar.gz (186.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

rightnow_cli-1.0.0-py3-none-any.whl (218.5 kB view details)

Uploaded Python 3

File details

Details for the file rightnow_cli-1.0.0.tar.gz.

File metadata

  • Download URL: rightnow_cli-1.0.0.tar.gz
  • Upload date:
  • Size: 186.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.6

File hashes

Hashes for rightnow_cli-1.0.0.tar.gz
Algorithm Hash digest
SHA256 0420879a24855266f5d409e515e37f87a93e9f285d9d3c791cfa39f147659e91
MD5 fdff5a3b341a4f7c82efcb25bc1f0d0c
BLAKE2b-256 f7ea224dddbaa57a3171dd765d79755b10554db1500d0534273ff86fcfde366f

See more details on using hashes here.

File details

Details for the file rightnow_cli-1.0.0-py3-none-any.whl.

File metadata

  • Download URL: rightnow_cli-1.0.0-py3-none-any.whl
  • Upload date:
  • Size: 218.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.6

File hashes

Hashes for rightnow_cli-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 a6911d755a52dcbbbbc6e53463da3575faf54e45135c914ed0fd0b9d32c273da
MD5 abf7350add6a34bda66d42a0c56cdeb9
BLAKE2b-256 3d6950cdc04643972b4b230128c44f2228e1287c7412ece617b6682980b2de1c

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page