Caliban User Guide
Caliban is a Rust-native, provider-agnostic AI agent harness that puts you in control
of model routing, memory, permissions, and prompt context.
This guide is for users who run caliban day-to-day and operators who deploy
and configure it for a team or homelab; it describes behavior and workflows, not Rust internals.
How this guide is organized
| Part | What it covers |
|---|---|
| Introduction | What Caliban is, why it exists, and current project status |
| Getting Started | Installation & building, your first session, the interactive TUI, and headless basics |
| Providers & Models | Supported providers, API key setup, model selection, and the model router |
| Configuration | Settings layering across four scopes, file locations, and the full settings reference |
| Permissions | Core concepts, the pattern grammar, permission modes, and rule management |
| Reference | CLI flags, settings schema, slash command index, environment variables, and file paths |
Caliban v0.1.0 is a pre-release. The core feature set is daily-usable on main under
AGPL-3.0. See Project Status for what is
shipped versus planned.