#nvidia

Lightweight self-hosted NVIDIA GPU fleet monitoring with read-only agents, secure ingestion, compressed storage, and a responsive React dashboard.

Reproducible token-throughput benchmark for OpenAI-compatible LLM servers, tuned for NVIDIA Spark and GB10 inference.

Open hardware desktop AI node: 4× Tesla V100, 128GB HBM2, PCIe/NVLink topology and V-Core liquid/air cooling.

Production-oriented Kimi K3 inference control plane with checkpoint release gates, MoE capacity planning, OpenAI gateway, NVL72 deployment, benchmarks, and observability.

GPU-accelerated Manim workspace + 14 Agent Skills + a 5,523-symbol offline API index, so coding agents can drive Manim as an API instead of guessing. NVENC encoding via a PyAV patch, ManimCE 0.21 and ManimGL/wgpu side by side, reproducible benchmarks, and verified corrections to widely-repeated docs.

On/off switch for routing Claude Code through a local model instead of Anthropic Pro/Max subscription. No API keys, no cloud fallback—local mode either works or fails cleanly. (tldr; Route Claude Code through a local model via Distrobox, powered by llama.cpp and LiteLLM.)

NVIDIA DGX Spark power user and edge AI maximizer

MindFoundry — NemoClaw-secured long agent for NVIDIA Agent Hackathon. Builds AI replicants of your teammates and answers ops questions with cited Nemotron synthesis.