Nvidia

ODS is a self-hosted AI server platform that bundles Ollama, Open WebUI, n8n, ComfyUI, and related tools into a single installation for running LLM...

OpenWhispr is a privacy-first, open-source voice-to-text application for macOS, Windows, and Linux that supports both local models (Whisper, NVIDIA...

Nemotron is NVIDIA's developer hub for training, fine-tuning, and deploying the Nemotron family of open models optimized for agentic AI workflows. It...

InferenceX is an open-source continuous inference benchmarking research platform that tracks real-time performance of LLM inference frameworks across...

Selkies is an open-source WebRTC-based remote desktop streaming platform optimized for low-latency GPU-accelerated Linux environments, designed for...

HAMi is a Kubernetes-native GPU virtualization and heterogeneous accelerator scheduling platform that enables sharing of expensive GPUs (NVIDIA,...

FluidAudio is a Swift SDK for running audio AI models (speech recognition, text-to-speech, voice activity detection, speaker diarization) locally on...

A CLI tool that discovers, benchmarks, and configures 191+ free coding LLM models across 20 providers, calculating real-time stability scores and...

cuda-oxide is an experimental Rust-to-CUDA compiler that enables writing GPU kernels directly in safe, idiomatic Rust without DSLs or foreign...

FlashInfer is a specialized GPU kernel library designed for high-performance LLM inference, providing optimized implementations for attention, GEMM,...

OptiScaler is a specialized tool for gaming that intercepts and replaces upscaling technologies (DLSS2+, FSR2+, XeSS) and frame generation in games...

NeMo Data Designer is a framework for generating high-quality synthetic datasets from scratch or using seed data, with support for statistical...

NeMo Guardrails is an open-source toolkit for adding programmable safety controls to LLM-based conversational applications, enabling developers to...

NCCL is a specialized GPU communication library that implements collective operations (all-reduce, all-gather, broadcast, etc.) optimized for...

G-Helper is a lightweight system utility that replaces Asus's Armoury Crate software for controlling power profiles, fan curves, RGB lighting, and...

LACT is a Linux desktop application for monitoring and controlling AMD, Nvidia, and Intel GPUs, offering detailed system information, overclocking,...

OpenNOW is an open-source desktop client for NVIDIA's GeForce NOW cloud gaming service, built with Electron and TypeScript. It allows users to browse...

NVIDIA NemoClaw is a reference stack for running AI agents (OpenClaw, Hermes, LangChain Deep Agents) securely inside NVIDIA OpenShell sandboxes with...

CUTLASS is a specialized library providing CUDA C++ templates and Python DSLs for implementing high-performance matrix operations (GEMM) and linear...

UCCL is a GPU communication library optimized for collective operations, peer-to-peer transfers, and endpoint communication across heterogeneous GPU...

NVIDIA TensorRT is an SDK for high-performance deep learning inference optimization on NVIDIA GPUs, with open-source components including plugins and...

NVIDIA GPU Operator automates the provisioning and management of GPUs in Kubernetes clusters by orchestrating NVIDIA drivers, container runtimes,...

cuML is a GPU-accelerated machine learning library that implements scikit-learn-compatible algorithms optimized for NVIDIA GPUs, delivering 10–50×...

Moonlight PC is an open-source GameStream client that enables remote game streaming from NVIDIA-equipped host PCs to Windows, macOS, Linux, and Steam...

A Prometheus exporter that collects NVIDIA GPU metrics via the nvidia-smi binary, enabling GPU monitoring on Windows, Linux, and macOS without...

NVIDIA Warp is a Python framework that JIT-compiles regular Python functions to GPU kernels for simulation, robotics, and machine learning workloads....

CCCL unifies three essential CUDA C++ libraries (Thrust, CUB, libcudacxx) into a single repository, providing high-performance parallel algorithms,...

nvitop is an interactive NVIDIA GPU process viewer and management tool for Linux systems, serving as a htop-like alternative to nvidia-smi. It's...

GPU Hot is a real-time NVIDIA GPU monitoring dashboard designed for DevOps engineers and ML/LLM practitioners who need to track GPU utilization...

dstack is a vendor-agnostic orchestration platform for GPU workloads (training, inference, agentic tasks) that abstracts across NVIDIA, AMD, TPU, and...