Berth documentation

Berth decides who gets your GPU. Engines, games and GPU apps lease the card in turn, so two of them never load at once and crash each other. The project README has the overview, the quick start and screenshots. These pages are the reference.

Page	What it covers
Install	The agent prompt, manual install, berth.toml, uninstall
Engines	Every engine Berth reads, API keys, ComfyUI as a suite
Leasing, games and holds	Priorities, drains, stuck releases, the juggle guard, minimum turns, claims and berth hold
VFIO passthrough (experimental, Linux)	berth vfio status, berth vfio run, the IOMMU requirements, an example switch script
Models	berth pull, integrity checks, shelves, berth storage, the page cache and berth prefetch
Gateway	One OpenAI-compatible port, cold starts, fallbacks, KV snapshots, switch costs, wake pages, park in RAM
The harbor and telemetry	Stowaways, the collisions board, alerts, every harbor panel, what Berth measures
Interfaces	The CLI's output contract and exit codes, the harbor's options, Prometheus
Benchmarks	Tested hardware and measured swap times
Roadmap	Phases, what each release shipped, what comes next
FAQ	Common questions, Docker engines included

Engine recipes for berth run are in contrib/INTEGRATION.md, and every release's changes are in the CHANGELOG.