Embedding models understand meaning; generative models write text. Here is how Google’s EmbeddingGemma differs from an LLM, and how they pair up in RAG.

A complete operator’s guide to Claude Code — project memory, permissions, plan-first execution, and multi-agent orchestration patterns.

A reference on Moltworker, an open-source project that runs the Moltbot personal AI agent on Cloudflare’s serverless platform instead of dedicated local hardware.

Explains AI architecture at two layers — the internal Transformer model and the external system pattern (prompting, RAG, fine-tuning, agents) — and how to choose between them.

Markdown is no longer just for formatting. Learn how frameworks like gstack use structured text to constrain AI agents to defined roles and keep multi-step work coherent.