RightNow AI

RightNow AI

#1 GPU AI Code Editor

4.7•10 reviews•

1.7K followers

Visit website
RightNow AI is the #1 GPU AI code editor. It combines GPU profiling, benchmarking, AI optimization, GPU virtualization, and a full GPU emulator in one environment to help developers analyze and optimize CUDA code faster
This is the 10th launch from RightNow AI. View more
Forge Agent

Forge Agent

Launching today
Swarm Agents That Turn Slow PyTorch Into Fast GPU Kernels
Forge turns PyTorch models into optimized CUDA and Triton kernels automatically. 32 AI agents run in parallel, each trying different optimization strategies like tensor cores, memory coalescing, and kernel fusion. A judge validates every kernel for correctness before benchmarking. We got 5x faster inference than torch.compile on Llama 3.1 8B and 4x on Qwen 2.5 7B. Works on any PyTorch model. Free trial on one kernel. Full credit refund if we don't beat torch.compile.
Forge Agent gallery image
Forge Agent gallery image
Forge Agent gallery image
Forge Agent gallery image
Forge Agent gallery image
Free Options
Launch tags:Hardware•Developer Tools•Artificial Intelligence
Launch Team / Built With
Auth0
Auth0
Start building with Auth0 for AI Agents, now generally available.
Promoted

What do you think? …

Jaber Jaber
RightNow AI
Maker
📌
Hey PH! If we don't beat torch.compile you get your credits back!! Real results on B200: Llama 3.1 8B: 5x faster than torch.compile Qwen 2.5 7B: 4x faster SDXL UNet: 3x faster
Daniele Packard

Congrats! Can you dictate rules that the judge uses?

Jaber Jaber
RightNow AI
Maker
@daniele_packard currently no but nice point! We will make you able to edit the rules for the judger
Curious Kitty
Product Hunt
Correctness is the main risk with generated kernels. What is your validation strategy beyond “matches reference outputs”—e.g., tolerances, randomized testing across shapes/dtypes, determinism, and how you debug/report failures so users can trust and iterate quickly?