FrenchForet — LLM Engineering

Four hands-on, foundations-first courses for building with large language models — from your first raw HTTP call to an agent with a knowledge-graph memory that stays inside its context window and watches itself with feedback loops you can trust.

Start with Foundations View on GitHub

Four courses. Do the Foundations course first; Agent Memory, Context Compression, and Feedback Loops are siblings that each assume it and build on top — read those in any order.

You write every line

Each lesson guides you through building small scripts yourself. A runnable reference solution for everything lives under examples/.

One hosted endpoint

Every example targets an OpenAI-compatible server (vLLM serving gpt-oss-120b). Point three environment variables at it and go; embeddings can use a separate endpoint.

Security throughout

Security is a through-line, not a chapter — every lesson ends with a topic-specific note, and isolation gets dedicated sections.