Public GitHub footprint of RightNow

Open-source Agent Operating System

Run a 1-billion parameter LLM on a $10 board with 256MB RAM

Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.

Pure Triton kernels for Qwen3.5-27B inference on NVIDIA B200

Claude Code for CUDA. Free AI assistant that actually understands GPU architecture

Comprehensive GPU specifications database with 2,824 GPUs across NVIDIA, AMD, and Intel

Minimal TPU implementation with 8x8 systolic array and PyTorch integration

Dynamic weight generation for recursive transformers via input-conditioned LoRA modulation

Dynamic per-token early exit for LLM inference. Skip layers tokens don't need

An agent harness that compiles a model into one provably-correct, self-retargeting CUDA megakernel and self-tunes it past cuBLAS at batch-1 LLM decode.

Memory-bounded compressed sparse attention via streaming top-k. Triton kernels for the DeepSeek-V4 lightning indexer. 32x regime extension on a single H200 | by RightNow https://www.rightnowai.co/

Open-source transpiler for CUDA Tile (13.1) migration

GPU CI/CD tool that tests CUDA kernels across multiple GPUs in parallel - Part of RightNow

Open-source web-based GPU performance visualization tool that transforms NVIDIA profiling data into interactive insights for CUDA engineers. Features timeline views, flame graphs, heatmaps, and AI-powered bottleneck detection.

Forge: Swarm Agents That Turn Slow PyTorch Into Fast CUDA/Triton Kernels

Hierarchical Causal Latent State Machines for Object-Centric World Modeling

RightNow Arabic LLM Corpus - One of the largest high-quality Arabic text datasets for LLM training

Official RunInfra SDK (TypeScript + Python) — optimized inference deployments