R_REDDYX.XYZ

Nvidia: open-source projects on GitHub

24 repositories on Nvidia, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.

// RELATED TOPICS

LLM 2094Self Hosted 359Local AI 82GPU 48Llama Cpp 56AI Agents 1319Amd 16Speech To Text 66Cuda 48Vllm 69Inference 95Ollama 249Comfyui 51RAG 533
Osmantic/ODS

ODS - YOUR AI SERVER

ODS turns any computer into a powerful AI server: LLM inference, chat, voice, agents, RAG, and image generation.

★ 7,832 · Shell
OpenWhispr/openwhispr

OpenWhispr: Voice Dictation

An app for speech-to-text conversion with support for local (Nvidia Parakeet/Whisper) and cloud models (BYOK). Privacy first, available on all platforms.

★ 3,216 · TypeScript
NVIDIA-NeMo/Nemotron

NVIDIA NEMOTRON: TRAINING RECIPES AND DEPLOYMENT

NVIDIA repository with training recipes, deployment guides, and usage examples for Nemotron models. Supports multimodal agents with up to 1M token context.

★ 2,361 · Jupyter Notebook
NVIDIA-NeMo/DataDesigner

NVIDIA Data Designer

NeMo Data Designer: generation of high-quality synthetic data from scratch or based on seed data. Ideal for training and fine-tuning models.

★ 1,877 · Python
utkuozdemir/nvidia_gpu_exporter

NVIDIA GPU METRICS FOR PROMETHEUS

Exporter of NVIDIA GPU metrics to Prometheus in Go. Monitoring temperature, utilization, and memory via nvidia-smi.

★ 1,590 · Go
uccl-project/uccl

UCCL: GPU Communication at Max

A fast library for efficient data exchange between GPUs: collective operations, P2P, and inference acceleration.

★ 1,586 · C++
psalias2006/gpu-hot

🔥 GPU REAL‑TIME DASHBOARD

GPU-hot — a web dashboard for monitoring NVIDIA GPU showing temperature, load, and memory in real time. Already over 1,500 stars on GitHub! 🌟

★ 1,543 · JavaScript
LilMGenius/paperthin

PAPERTHIN: SKILLS FOR RECURSIVE RSI

OpenAI hackathon winner's project on recursive agent self-improvement. Unpacks NVIDIA's zero-touch proof into engineering practice. Ready skillset for autonomous coding a

★ 1,445 · JavaScript
aiptimizer/TurboOCR

FAST OCR SERVER ON GPU

TurboOCR — a lightning-fast OCR server on TensorRT FP16 with PP-OCRv5 support, processing 270 images/sec on FUNSD via HTTP + gRPC API.

★ 1,160 · C++
SemiAnalysisAI/InferenceX

InferenceX – Inference Benchmark

Open-source continuous inference benchmark for Qwen3.5, DeepSeek, GPTOSS and new accelerators.

★ 1,016 · Python
kaito-project/aikit

Survive LLM Chaos

Open-source Go tool for fine-tuning, building, and deploying LLMs with a single command.

★ 545 · Go
ttlequals0/MinusPod

REMOVES ADS BEFORE PLAYBACK

MinusPod — a self-hosted Python server that intercepts media streams and removes ads before playback using LLM Claude. Users get clean content without interruptions, with

★ 545 · Python
Light-Heart-Labs/DreamServer

DreamServer: Local AI

DreamServer is an open-source project for running LLMs locally with a chat interface, voice control, agents, workflows, RAG, and image generation, operating without cloud

★ 523 · Python
AbdoKnbGit/tau

TAU: Dev Agent Orchestrator

A single orchestrator for managing dev agents, sessions, and environments. Everything under control.

★ 429 · TypeScript
reid41/QA-Pilot

QA‑PILOT CHAT ASSISTANT FOR CODE

QA‑Pilot — an interactive chat that uses online or local LLMs for quick understanding and navigation of any GitHub repository. The project helps find functions, explain c

★ 329 · Svelte
T-Crypt/berth

GPU BY TURN WITHOUT CRASHES

Berth leases the GPU to chat, image, and voice engines in turn. Two processes never load together and crash each other. Single Go binary, no dependencies.

★ 297 · Go
beehive-lab/jitllm

JITLLM: HIGH PERFORMANCE LLM ON JVM

JITLLM — Java framework for high‑performance LLM inference and serving on the JVM. Supports GPU acceleration, GGUF and quantized model formats, and integration with DeepS

★ 295 · Java
defilantech/LLMKube

LLMKUBE: LLM IN KUBERNETES

LLMKube - Kubernetes operator for LLM inference on heterogeneous GPU fleet: NVIDIA CUDA, AMD Vulkan, Apple Silicon Metal. Supports llama.cpp, vLLm, TGI, mlx-server, multi

★ 266 · Go
NVIDIA/NeMo-Relay

RUST RUNTIME FOR AI AGENTS

NeMo-Relay is a multi-language runtime for AI agents in Rust. Manages execution scope, lifecycle events, and middleware for tool and LLM calls. 201 stars on GitHub.

★ 245 · Rust
SikamikanikoBG/homelab-monitor

HOMELAB MONITOR DASHBOARD

Plug‑and‑play dashboard for homelab in a single container: monitoring GPU, local‑AI VRAM, Docker, systemd and host health. Built‑in read‑only MCP server gives AI agents a

★ 236 · Python
DevDock-AI/Speedy

125B MoE Inference on RTX

Run Qwen3.8-Flash-Next (125B MoE) with 1M context on one or two RTX 3080 10GB cards. Tuned, benchmarked fork of Strata.

★ 71 · C++
stevibe/SparklingKit

SparklingKit: Local AI Platform

SparklingKit — a local toolkit for OCR, transcription, translation, image generation, and mind‑map creation, enabling composable workflows on DGX Spark.

★ 70 · TypeScript
Somnusochi/VLM-AutoYOLO

Auto-labeling YOLO Training

Platform for automatic image and video labeling using VLM NVIDIA LocateAnything-3B, with manual correction and one-click YOLO model training.

★ 31 · Python
zorost/sparkduet

SparkDuet: on-demand model library

The project provides a single OpenAI‑compatible endpoint for running DeepSeek and Qwen models. It serves them via two vLLM lanes (TP=2) on an NVIDIA DGX Spark cluster and

★ 0 · Python

New projects on this topic in Telegram

Telegram →
Nvidia — 24 open-source GitHub projects | REDDYX AI