NVIDIA DGX Spark integration for Claude Code — local model serving, GPU monitoring, VM management, and hybrid AI workflows
Plugin dgx-spark from marketplace dgx-agentskills in jeremyeder/dgx-agentskills. Commands read from the repo's manifest — 1 month ago.
spark-hybridConfigure Claude Code to use the DGX Spark as a model backend — full local, hybrid (Opus primary + Spark for subagents), or failover mode. Use when switching between local and cloud inference, pointing Claude Code at Spark, or setting up hybrid workflows. Triggers on: "use local model", "switch to S
spark-modelsManage AI models on the DGX Spark — list, pull, serve, stop, and recommend models across Ollama and vLLM backends. Use when deploying models, checking what's running, pulling new models, or getting recommendations for a use case. Triggers on: model names (Qwen, Llama, DeepSeek, Gemma), "serve model"
spark-setupSet up and provision an NVIDIA DGX Spark from scratch or after factory reset. Use when configuring a new Spark, recovering from reset, or verifying system state. Triggers on: "set up DGX Spark", "configure Spark", "provision Spark", "factory reset".
spark-vmsManage KVM/QEMU virtual machines on the DGX Spark. Create, start, stop, and snapshot VMs on the ARM64 hypervisor. Use when running VMs, creating virtual machines, or managing virtualization on the Spark. Triggers on: "create VM on Spark", "virtual machine", "KVM", "run Windows on Spark".
spark-vpnSet up and manage Tailscale VPN on the DGX Spark for remote access. Use when configuring remote access, setting up Tailscale, or troubleshooting VPN connectivity. Triggers on: "Tailscale", "VPN", "remote access to Spark", "access Spark from outside".
/dgx-spark:spark-models/dgx-spark:spark-status/dgx-spark:spark-switchspark-monitorBackground health monitoring agent for the DGX Spark. Periodically checks system status and alerts on state changes. Use when you want ongoing awareness of Spark health during a long session.
dgx-sparkconnects to: http://jeder-spark.local:3100/mcp
AMD's verified Agent Skills in one plugin: route image/audio through local AI on Ryzen AI, serve LLMs on AMD Instinct GPUs with vLLM, optimize inference throughput with Hyperloom, and analyze GPU kernel and PyTorch trace performance.
21 skills
NVIDIA DGX Spark (GB10) environment operations. Use when setting up, preflighting, or debugging ML workloads on DGX Spark or aarch64 Blackwell hardware — CUDA-13 wheel/ABI checks, unified-memory OOM ladders, thermal monitoring.
3 skills · 1 command · 1 agent
Production LLM inference including vLLM, TensorRT-LLM, llama.cpp, and SGLang. Use when deploying models for production inference.
98 skills
Find the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, and other NVIDIA-powered workflows.
1 skill
Run AI models locally with Ollama - free alternative to OpenAI, Anthropic, and other paid LLM APIs. Zero-cost, privacy-first AI infrastructure.
1 skill · 1 command
Operate NVIDIA DGX Cloud Lepton through the globally installed `lep` CLI.
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.