Open source repositories tagged with #nvidia, ranked by health score.
Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference
Frontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.
A Python framework for GPU-accelerated simulation, robotics, and machine learning.
cuda-oxide is an experimental Rust-to-CUDA compiler that lets you write (SIMT) GPU kernels in safe(ish), idiomatic Rust. It compiles standard Rust code directly to PTX — no DSLs, no foreign language bindings, just Rust.
UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)
Lightweight Armoury Crate alternative for Asus laptops with nearly the same functionality. Works with ROG Zephyrus, Flow, TUF, Strix, Scar, ProArt, Vivobook, Zenbook, Expertbook, ROG Ally, and many more.
PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT
FlashInfer: Kernel Library for LLM Serving
Platform for deploying and routing GPU-accelerated inference, streaming, and batch workloads at scale.
Beginner's Guide to reComputer Jetson
