Ai-Docs
llms.txt for this section · raw markdown mirror
- 01 — Architecture
— The two-tier pattern
raw.md - 02 — Context Sizing & Model Quantisation
— The VRAM budget equation
raw.md - 03 — Primary vs Secondary `llama-server`
— Why two servers, not one
raw.md - 04 — Sub-agent Use
— The core idea
raw.md - 05 — Open Terminal & Tooling
— What Open Terminal is
raw.md - 06 — Skills
— What a skill is
raw.md - 07 — Dual-Use: Inference Server ⇄ Gaming/Desktop
— The problem
raw.md - 08 — Build Instructions
— How to build from scratch
raw.md - AI Machine — Concepts & Tips
— This directory documents a self-hosted AI inference and application stack: native `llama.cpp` inference servers on the GPUs, fronted by a Docker application tier (Open WebUI, Open Terminal, Pipelines)…
raw.md