Concepts

These pages explain how Tryll thinks — the mental models behind the server, the client libraries, and the workflows you build on top of them. Read one when you want to understand why something works the way it does; reach for a how-to guide or the reference when you want to do a specific thing or look up a specific field.

Start with these

• Architecture at a Glance — the 10-minute tour. Server → session → agent → graph → node → model. Every later page fits inside this frame.
• Agents and Sessions — who owns what, and how a conversation comes into and goes out of existence.
• Lifetime and Ownership — how string storages, embedded string storages, and models stay alive across agents, turns, and sessions.
• Workflows, Graphs, and Nodes — the building block that turns a model into an application.

Dive into the pieces

• Models and Inference Engines — language vs. embedding models, variants per backend, what the KV cache does.
• Retrieval-Augmented Generation (RAG) — how Tryll grounds answers in your data: chunking, embeddings, cosine distance, and where retrieved text lands in the prompt.
• Tool Calling — making small local models invoke tools: format families, limits, what the detection-only design means for your game or app.
• Projection and Token Budgets — how a growing dialog is turned into a bounded prompt, turn after turn, without losing the session.

How these relate to the rest of the docs

flowchart LR
    C[Concepts<br>why & mental model] --> R[Reference<br>fields & semantics]
    C --> H[How-to<br>task recipes]
    H --> R
    T[Tutorials<br>first inference] --> H
    T --> C

Every concept page links down to the specific reference pages that make its ideas concrete, and to the how-to guides that put them to use.