# Code Editor

```
┌───┐
│GPU│
└───┘
```

## FREE

### SOLO DEVELOPERS

#### DEPLOYMENT
- Single GPU development
- Unlimited profiling & benchmarking
- CodeLens performance metrics
- GPU virtualization

#### AI FEATURES
- Local LLM support
- 1 Forge credit/mo

#### SUPPORT
- Community support [Join our Discord](https://discord.gg/sSJqgNnq6X "Join our Discord")

**$0/mo**  
[GET STARTED](https://dashboard.rightnowai.co/)

```
┌───┐──▸┌───┐
│GPU│──▸│GPU│
└───┘──▸└───┘
```

## PRO

### PROFESSIONAL TEAMS

#### DEPLOYMENT
- Everything in Free
- GPU emulator access (50+ GPUs)
- Multi-GPU comparison (6 max)
- Natural language profiling

#### AI FEATURES
- 1 Forge credit/mo
- 1000 AI Agents credits/mo
- Unlimited autocomplete
- GPU-optimized suggestions

#### SUPPORT
- Priority email support

**$20/mo**  
[GET PRO](https://dashboard.rightnowai.co/login?plan=pro&billing=monthly)

```
┌───┐─┌───┐
│GPU│─│GPU│
├───┤─├───┤
│GPU│─│GPU│
└───┘─└───┘
```

## FORGE

### AI KERNEL OPTIMIZATION

#### WHAT YOU GET
- Save thousands on GPU costs
- Improve speed of your AI models
- Improve efficiency
- All GPU architectures

#### INFRASTRUCTURE
- Dedicated infrastructure
- On-premise deployment
- Custom SLA & support
- NDA & IP protection

#### SUPPORT
- Dedicated support team

**Custom Pricing**  
[CONTACT SALES](/content/enterprises/index.html)

### Feature Comparison

| Feature | Free | Pro | Forge |
| --- | --- | --- | --- |
| CORE FEATURES | | | |
| Smart Profiling | ✓Unlimited | ✓Unlimited | ✓Unlimited |
| Automated Benchmarking | ✓Unlimited | ✓Unlimited | ✓Unlimited |
| CodeLens Performance Metrics | ✓ | ✓ | ✓ |
| Local LLM Support (Ollama, vLLM) | ✓ | ✓ | ✓ |
| Automatic Kernel Fusion | ✓ | ✓ | ✓ |
| GPU Virtualization | ✓ | ✓ | ✓ |
| GPU Emulator | ✗ | ✓ | ✓ |
| Multi-GPU Performance Comparison | ✗ | ✓6 GPU Max | ✓Unlimited |
| Natural Language Profiling | ✗ | ✓ | ✓ |
| Multi-GPU Execution Analysis | ✗ | Coming Soon | ✓ |
| AI FEATURES | | | |
| Autocomplete Suggestions | ✓Limited | ✓Unlimited | ✓Unlimited |
| GPU-optimized Suggestions | ✗ | ✓ | ✓ |
| FORGE — KERNEL OPTIMIZATION | | | |
| Model Optimizations | ✗ | ✗ | ✓ |
| Drop-in Replacement Kernels | ✗ | ✗ | ✓ |
| Dedicated Infrastructure | ✗ | ✗ | ✓ |
| On-Premise Deployment | ✗ | ✗ | ✓ |

```
┌───┐
│GPU│
└───┘
```

## FREE

### ALWAYS FREE

**$0/mo**  
[GET STARTED](https://dashboard.rightnowai.co/)

- ▪ Unlimited smart profiling
- ▪ Unlimited automated benchmarking
- ▪ 1 Forge credit/mo
- ▪ Limited autocomplete
- ▪ CodeLens performance metrics
- ▪ Local LLM support
- ▪ Automatic kernel fusion
- ▪ GPU virtualization
- ✗ GPU emulator

```
┌───┐──▸┌───┐
│GPU│──▸│GPU│
└───┘──▸└───┘
```

## PRO

### SOLO DEVS

**$20/mo**  
[GET PRO](https://dashboard.rightnowai.co/login?plan=pro&billing=monthly)

- ▪ Unlimited smart profiling
- ▪ Unlimited automated benchmarking
- ▪ GPU virtualization
- ▪ GPU emulator access
- ▪ Automatic kernel fusion
- ▪ 1 Forge credit/mo
- ▪ 1000 AI Agents credits/mo
- ▪ Unlimited autocomplete
- ▪ GPU-optimized suggestions
- ▪ Multi-GPU performance comparison (6 GPU max)
- ▪ Natural language profiling
- ► Multi-GPU execution analysis (coming soon)

```
┌───┐─┌───┐
│GPU│─│GPU│
├───┤─├───┤
│GPU│─│GPU│
└───┘─└───┘
```

## FORGE

### AI KERNEL OPTIMIZATION

**Custom Pricing**  
[CONTACT SALES](/content/enterprises/index.html)

- Save thousands on GPU costs
- Improve speed of your AI models
- Improve efficiency
- ▪ All GPU architectures
- ▪ Dedicated infrastructure
- ▪ On-premise deployment
- ▪ Custom SLA, NDA & IP protection

## FAQs

**How is RightNow AI different from other code editors?**
The only editor built for CUDA. Hardware-aware AI, GPU emulator, real-time profiling, and benchmarking in one tool.

**What is Forge?**  
Enterprise-only AI kernel optimization. Generates optimized GPU kernels for any AI model, benchmarked against torch.compile(max_autotune). Contact sales to get started.

**Can I use my own API keys?**  
Yes. OpenRouter for 15+ providers or run offline with Ollama, vLLM, LM Studio.

**What GPUs are supported?**  
Editor supports all NVIDIA CUDA GPUs. Forge supports datacenter GPUs: B200, H200, H100, A100, L40S.

**Is my code private?**  
Yes. Use local LLMs to keep code on your machine. Forge includes dedicated infrastructure with no shared resources.

**System requirements?**  
NVIDIA CUDA Toolkit 11.0+ and any CUDA-capable GPU.