Phase 2 of the de-swarm project — how I turned a 3B text-to-SQL model into a production API for...
Shipping a Local LLM API with FastAPI and Ollama
Related
How an AI Terminal Assistant Became My Team's Most Productive Engineer - Opencode + Claude + MCP
We connected Claude to multiple tools n our tech stack via MCP. It found >$100K/month in waste, investigated incidents faster than our senior engineers, and sparked an AI agent eco...
GuardDuo — The AI Guardian That Keeps Vibe-Coding in Check
AI coding tools are incredible. But I noticed something — they ship code fast, skip the rules, and...
Choosing a Vector Database in 2026: pgvector vs. Pinecone vs. Qdrant vs. Weaviate vs. Milvus
Every RAG tutorial pulls the same move. It walks you through embeddings, chunking, retrieval, and...