Blog

The next step in my AI Agent's memory experiments: solving index bloat with Two-Tier Hierarchical Summary, hybrid scoring (semantic + importance + recency), and programmatic 1-hop related dates.

How I restructured my AI Agent's (Nouva) memory system from a noisy, bloated Vector DB into a lean, Two-Tier Hybrid RAG + NAS Markdown setup that covers 95% of personal needs.

Why were Docker and Kubernetes actually created? Instead of getting dizzy reading rigid theories about container orchestration, let's discuss the core philosophy behind solving stateful environments.

A classic homelab disaster story: how a misconfigured Terraform mount point backup triggered a crash loop, ate 200GB+ of storage, and caused massive SSD wear anxiety.

A comprehensive guide to building a self-hosted homelab architecture from physical bare-metal servers, Proxmox virtualization, Kubernetes (K3s) orchestration, to exposing it securely to the public internet.

A behind-the-scenes look at optimizing PostgreSQL. From connection leaks in Kubernetes, indexing overkill that killed bulk inserts, to stale cache disasters with Redis.

A behind-the-scenes look at why I abandoned traditional linear pipelines and switched to LangGraph to build more reliable, state-driven AI agents.

Why GraphRAG is often overkill for personal AI assistants and why I decided to pivot back to a simpler RAG + Memory stack for Nouva.

In the midst of cloud dominance, building an independent infrastructure (home-lab) remains the best choice for engineers who prioritize privacy, total control, and operational efficiency.

How to build autonomous agents with long-term memory using GraphRAG, Neo4J, and Graphitti.