We use privacy-friendly analytics to understand how visitors use this site. No cookies are set by default. Privacy Policy
Digital products and resources for AI, XR, and DevOps, plus art pieces.
The complete knowledge graph arsenal — from GraphRAG pipelines and Neo4j deployments to production monitoring and interactive visualization. Everything you need to ship knowledge graphs that scale.
Stop piecing together AI infrastructure from five different tutorials. Deploy Dify, n8n, Ollama, Qdrant, Prometheus/Grafana, and MinIO as one integrated system with monitoring, backup, and security pre-wired — in one command.
Support the development of GraphWiz.ai — every contribution fuels better content, open-source tools, and free educational resources.
Stop running PostgreSQL and Redis without a backup strategy — get production-grade persistence, WAL archiving, and recovery workflows in one deployable stack.
Production Ansible deployment for two DGX Spark (GB10) nodes with vLLM TP2, LiteLLM proxy, Prometheus/Grafana monitoring, and 200Gbps RoCE networking.
Deploy LLMs on a single NVIDIA DGX Spark (GB10) with 128GB unified memory — from zero to serving in under 5 minutes.
Stop wasting hours provisioning PostgreSQL, Redis, Weaviate, and Nginx for Dify — get a production-tuned, security-hardened stack with backup strategy and TLS termination.
Beat the vector-only ceiling — ship a hybrid GraphRAG pipeline that handles multi-hop questions your competitors can't answer.
Stop wrestling with abstract theory — implement Dijkstra, PageRank, and community detection in production systems with confidence.
From prototype to production — architect, deploy, and operate graph-powered retrieval at scale. The playbook that turns RAG engineers into architects who ship.
Go from zero to your first deployed knowledge graph — without the PhD.
AWS S3 eating your budget? Self-host MinIO on NVMe drives and break even at 5TB — with durability guarantees, backup strategy, and no egress fees.
Stop losing workflows when containers restart — deploy n8n with PostgreSQL persistence and Redis-backed queue so your automations survive restarts and scale.
Ship a hybrid RAG system that combines Neo4j graph traversal with vector search — so your LLM answers questions that pure vector RAG can't touch.
Stop debugging outages blind — deploy Prometheus, Grafana, Loki, and Alertmanager with pre-wired dashboards and alerts so you know about problems before users do.
Stop piecing together Ollama, Open WebUI, and LiteLLM from separate tutorials — deploy a complete self-hosted AI stack with GPU acceleration pre-wired.
Ship interactive graph visualizations that render 100K nodes without dropping frames — without the trial-and-error of WebGL debugging.
Stop exposing services without WAF protection — deploy Nginx with auto-renewing TLS, CrowdSec WAF, rate limiting, and security headers in one command.
Curated collections and discounted toolkits.
Master Docker, Kubernetes, Docker Compose, and Helm with these production-ready reference sheets
Terraform, Ansible, and Systemd — IaC and provisioning reference sheets for production
Metrics, logs, tracing, and alerting — the monitoring engineer's quick reference
Nginx, SSH, and network tools — the essential networking reference for DevOps
8 research papers — LLM evaluation, advanced math, VR affordances, AI alignment, and more
PostgreSQL, Redis, and Neo4j — query patterns, config, and admin commands in one reference
Get notified when I publish new articles on AI infrastructure, DevOps, and XR development.