Syntax is your fully managed, privately owned, general-purpose AI factory — a universal backend for deploying proprietary and open-source models across your own cloud accounts. These docs cover installation, configuration, supported harnesses and models, inference options, and dUX integration.
Introduction
What Syntax is, how the AI-factory model works, and why teams choose it.
Getting Started
Install on macOS, Linux, or Windows. Run your first session and connect a coding assistant.
Harnesses
Use Syntax with the bundled Syntax CLI, Codex, Claude Code, OpenCode, or Pi.
Inference
Local GPU/CPU/Apple Silicon, remote self-hosted, and managed remote on dUX.
Concepts
Party Builder, Plan Mode, Agent Handoff, Runtime Modes.
Syntax × dUX
How Syntax integrates with dUX for managed remote inference.
Differentiators
Why Syntax - first-class inter-compatibility, multi-engine inference, multi-model parties.