Havuz

Prompt-to-video Three.js skill: 3D scenes, ImageGen-assisted reassembly, lightweight HF/SimReady retrieval and deterministic MP4 rendering.

Qwen3.8-Flash-Next (125B MoE) up to 1M context on one or two RTX cards (tuned on 3080 10gb). A measured, tuned and benchmarked fork of Str

Windows utility focused on cuda setup, nvidia local AI, and cuda environment for local AI workflows.

A decision library for running local LLMs on multi-GPU machines without NVLink: parallelism, communication, quantization, speculative decodi

A code reviewer that reports only what it can prove: a test that shows the bug, or the data that confirms the risk. Open source, built by a

Qwen3.8-Flash-Next (180B MoE) on one 12-16 GB NVIDIA GPU, Linux or Windows. Own engine, own compression.

Berth is a lightweight GPU resource manager written in Go. It controls which applications get access to your GPU, when they get it, and how

面向 DeepSeek Harness 的本地图像生成插件（优化版）：经本机 ComfyUI 调用 Qwen-Image 2.1 生成图像，全部流量限于 127.0.0.1。本版增强推理性能、NVIDIA/Intel/AMD 显卡适配与 Windows/Linux 兼容。原作者

Distributed image and video generation in ComfyUI for two NVIDIA DGX Sparks.

Serve your models fast on your own infra in 3 steps.

Kyojin: open-source engine that runs 100 GB-class open models (GLM-5.3, Qwen3.8, DeepSeek V4.1) on one desktop machine. AMD Strix Halo, NVID

Automate ongoing market research with an AI planner, Jules agents, live conversations, and organized GitHub reports.

Local image generation and editing for NVIDIA DGX Spark, powered by Qwen-Image-2.1 and Gradio.

High-performance CUDA inference engine for Qwen models, written from scratch in C++/CUDA

Local-first AI workbench for OCR, transcription, translation, image generation, mind maps and composable workflows. Built for DGX Spark.

Docker compose configs for serving Qwen3.8-27B on a DGX Spark (GB10): vLLM+MTP current, SGLang+DSPARK + FP8 rollback stacks

dgx-spark-qwen38 is an open-source installer that turns an NVIDIA DGX Spark, or any GB10 machine (ASUS, Dell, HP, Lenovo, MSI, GIGABYTE, Ace

A tiered-memory system design for workloads that don't fit in RAM: measure the working set, pin the hot tier, stream the cold tier from flas

See every GPU in your lab in the terminal, the browser or a report — who holds each GPU, which ones sit idle. One Python file, nothing to in

Run NVIDIA's tri-modal Nemotron Omni (text+vision+audio) entirely on Apple Silicon — pure MLX runtime, parity-verified against NVIDIA's refe

Catch local LLMs spilling into the CPU. One run shows GPU placement, prefill, decode, memory, power and a verdict.

Free NVIDIA DLI course: build, coordinate, and secure AI agents with NemoClaw and OpenShell. Browser-based, no GPU required. Available in En

MCP server for NVIDIA GPU metrics give AI agents real-time access to GPU utilization, memory, temperature, and power

Distill teacher chains-of-thought into a LoRA adapter via a strict boxed-answer format contract + two-phase Train→Nudge (silver-medal NVIDIA

Self-hosted vLLM made simple. Git-friendly YAML for models and profiles, full lifecycle from an intuitive CLI and TUI.

Offline-first Python AI agent that runs a tiny research business: quotes each job against its own costs, collects via Stripe, fulfils with N

Hardware-aware post-install for Fedora 45 KDE Plasma 6 on Wayland: NVIDIA, AMD or Intel, desktop or laptop, dual-boot. Low-latency gaming, K

The old advice to avoid Windows for local LLMs used to be right. It isn't anymore. The fixes for display-GPU desktop crashes and WSL memory

CPU-side action routing, context compression, and causal memory for AI agents — matches an LLM-everything agent at 58% fewer LLM calls and ~

Dual-engine (llama.cpp + vLLM) LLM benchmarking pipeline for GGUF & safetensors on NVIDIA GPUs — speed, quality, live dashboard, publishable

Self-hosted homelab dashboard in one container — GPU, local-AI VRAM, Docker, systemd, energy costs. Read-only MCP server so AI agents can ex

Your reading list, as a podcast you own

Production-ready, bleeding-edge, upstream-first vLLM Docker image for the NVIDIA DGX Spark (GB10 / sm_121a), verified against real models on

让 Codex 白嫖 NVIDIA 免费顶级模型，一键接入 | Transparent proxy between Codex and NVIDIA NIM — use NVIDIA's free hosted top-tier models with Codex

The visual compute platform for AI and robotics — connecting agents, GPU workloads, simulation, training, and real robots through typed work

Object-storage-native KV cache for LLM inference & RL. Cross-restart, cross-conversation, cross-engine via shared S3 bucket.

Zero-dependency Go proxy for rotating free-tier AI API keys. No more 429s.

⚡ Adaptive multi-model LLM router — 80+ providers, Jev System One single-pass routing (model=jev-auto), pheromone-trail failover, parallel e

NeMo Helix: Make the agents you ship faster, more accurate, and safer.

Realtime TUI monitor for local LLM servers (ollama, llama.cpp). The only GPU monitor that knows what model is running and how much each toke

📊 Automated hourly benchmarks for 20+ NVIDIA NIM models — interactive dashboard, zero infra, self-hostable. Open-source & community-driven.

Real-time hardware and LLM inference monitoring — GPU, CPU, memory, and vLLM metrics streamed to a dashboard.

DFlash vLLM for DGX Spark — Plug & Play Block-Diffusion Speculative Decoding

Self-hosted AI code review for GitHub pull requests.

Unified KV-cache compression for LLM inference: 12 Python-native methods, guarded add-on composition and routing, analytical capacity simula

Your adaptive AI agent for your work.

OpenAI-compatible gateway aggregating 8 free LLM providers with automatic failover, circuit breakers, and smart routing. 32+ models, zero c

Browser-based model and inference management for NVIDIA DGX Spark - inventory local and Hugging Face models, manage Ollama and LiteLLM, gene

Hermes Agent (NousResearch) sandboxed by NVIDIA OpenShell — hardware-enforced network/filesystem/syscall policy, full memory + gateway stack