Docker configuration for running VLLM on dual DGX Sparks

Collection of step-by-step playbooks for setting up AI/ML workloads on NVIDIA DGX Spark devices with Blackwell architecture.

A compile step for knowledge bases. Gives your agent a concept graph of your content — under 20s to index, 8ms queries on device.

Agent Skill for exploring Obsidian vaults with Enzyme — self-contained, cross-agent compatible

Self-host Honcho memory layer for Hermes Agent — OpenRouter + Venice, no code changes

autonomous harness engineering

sparkrun - launch, manage, and stop LLM inference workloads on NVIDIA DGX Spark systems

Official Spark Arena Recipe Registry

Entrpi/ds4, a Blackwell CUDA perf fork of antirez/ds4 on NVIDIA DGX Spark: one-command install, ~3x upstream prefill, ~1.5x decode, DSpark, and full continuous batch support

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

Personal AI, On Personal Devices