# Syntax Docs

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. This index lists every page in the public documentation. The full Markdown corpus is at https://docs.syntax-ftc.com/llms-full.txt.

- [Frequently Asked Questions](https://docs.syntax-ftc.com/docs/faq): Quick answers to the questions that come up most often when evaluating or starting with Syntax.
- [Glossary](https://docs.syntax-ftc.com/docs/glossary): A short, capability-level glossary of Syntax-specific terms.
- [Welcome to Syntax](https://docs.syntax-ftc.com/docs): Syntax is your Fully Managed, Privately Owned, General-Purpose AI Factory.
- [User-visible flags reference](https://docs.syntax-ftc.com/docs/cli/flags): The flags you'll actually use day-to-day across `syntax` and `syntax-cli`.
- [CLI overview](https://docs.syntax-ftc.com/docs/cli/overview): The two Syntax binaries — `syntax` (the application command) and `syntax-cli` (the bundled coding harness) — and what each one is for.
- [Syntax Coding Harness](https://docs.syntax-ftc.com/docs/cli/syntax-cli): The Syntax coding harness — TUI sessions with Plan Mode, Runtime Modes, and the full agent experience, started via `syntax-cli`.
- [Syntax connect](https://docs.syntax-ftc.com/docs/cli/syntax-connect): Wire a coding assistant to the local Bridge. Reversible.
- [Agent Handoff](https://docs.syntax-ftc.com/docs/concepts/agent-handoff): When the context window fills up, Syntax writes a structured handoff and starts fresh — instead of in-place compaction that loses the thread.
- [Exposed endpoints](https://docs.syntax-ftc.com/docs/concepts/exposed-endpoints): Per-deployment OpenAI-compatible bearer tokens you can issue and revoke from the desktop app.
- [Memory](https://docs.syntax-ftc.com/docs/concepts/memory): Two-layer memory — always-on file-based memory plus an opt-in retrieval pipeline for session-spanning recall.
- [Observability](https://docs.syntax-ftc.com/docs/concepts/observability): Metrics, traces, crash dumps, and request logging for everything Syntax runs — controllable from the UI.
- [Party Builder & Specialists](https://docs.syntax-ftc.com/docs/concepts/party-builder): Compose a strong main agent, a cheaper sub-agent, and up to six specialists into a single deployment.
- [Plan Mode](https://docs.syntax-ftc.com/docs/concepts/plan-mode): Structured planning before execution — the agent proposes, you accept, then a fresh context fork actually runs the work.
- [Runtime Modes](https://docs.syntax-ftc.com/docs/concepts/runtime-modes): Default, AutoEdit, and Bypass — the three-state cycle that gates which tool calls run unattended.
- [Specialist Models](https://docs.syntax-ftc.com/docs/concepts/specialist-models): Specialists are non-main models that a multi-model party exposes as tools to the main agent.
- [Agent Handoff (vs compaction)](https://docs.syntax-ftc.com/docs/differentiators/agent-handoff): Long sessions don't degrade — at the long-context threshold, Syntax does a structured handoff to a fresh context instead of in-place compaction.
- [AI-agent-friendly docs](https://docs.syntax-ftc.com/docs/differentiators/ai-agent-friendly): This wiki ships as a website AND as a Markdown corpus AI agents can ingest in a single fetch.
- [First-class inter-compatibility](https://docs.syntax-ftc.com/docs/differentiators/first-class-inter-compatibility): The harnesses you already use and the models you actually want to run — both sides keep their full capabilities, and nothing in the middle is degraded.
- [Multi-engine inference](https://docs.syntax-ftc.com/docs/differentiators/multi-engine-inference): Hardware-aware engine selection across a large compatibility matrix — Syntax owns the optimization work so you don't.
- [Multi-model parties](https://docs.syntax-ftc.com/docs/differentiators/multi-model-parties): One main agent, one sub-agent, up to six specialists — composed into a single deployment with capability scoring and a unified plan.
- [Managed remote vs self-managed remote](https://docs.syntax-ftc.com/docs/dux-integration/differences-vs-self-managed): When to pick which path — capability, control, and cost tradeoffs.
- [Managed remote on dUX](https://docs.syntax-ftc.com/docs/dux-integration/managed-remote): The developer-facing flow — pick a model, pick a tier, deploy. dUX handles the rest.
- [Syntax × dUX](https://docs.syntax-ftc.com/docs/dux-integration/overview): How Syntax integrates with dUX for managed cloud GPU — what each side owns, what each side contributes.
- [Permissions & IAM](https://docs.syntax-ftc.com/docs/dux-integration/permissions-and-iam): Identity boundaries between Syntax and dUX, and what each system enforces.
- [Connecting a coding assistant](https://docs.syntax-ftc.com/docs/getting-started/connecting-a-harness): How `syntax connect` wires your existing harness to Syntax, and how to disconnect cleanly.
- [First launch](https://docs.syntax-ftc.com/docs/getting-started/first-launch): What happens the first time you open Syntax and how to land on a working setup in under five minutes.
- [Install on Linux](https://docs.syntax-ftc.com/docs/getting-started/install-linux): Install Syntax on Ubuntu 20.04+, Debian 11+, Fedora 38+, or any modern x86_64 / aarch64 distribution.
- [Install on macOS](https://docs.syntax-ftc.com/docs/getting-started/install-macos): Install Syntax on macOS 12 (Monterey) or later.
- [Install on Windows](https://docs.syntax-ftc.com/docs/getting-started/install-windows): Install Syntax on Windows 10 (21H2) or later, with full native and WSL2 paths.
- [Claude Code](https://docs.syntax-ftc.com/docs/harnesses/claude-code): Use Anthropic's Claude Code CLI with Syntax.
- [Codex](https://docs.syntax-ftc.com/docs/harnesses/codex): Use OpenAI's Codex CLI with Syntax.
- [OpenCode](https://docs.syntax-ftc.com/docs/harnesses/opencode): Use OpenCode with Syntax.
- [Harnesses overview](https://docs.syntax-ftc.com/docs/harnesses/overview): The coding assistants Syntax integrates with out of the box, and how the connect/disconnect lifecycle works.
- [Pi](https://docs.syntax-ftc.com/docs/harnesses/pi): Use Pi with Syntax.
- [Syntax CLI](https://docs.syntax-ftc.com/docs/harnesses/syntax-cli): Syntax's own native coding agent — always available, no separate install.
- [Hardware support](https://docs.syntax-ftc.com/docs/inference/hardware-support): What hardware Syntax runs on, and which capabilities each tier unlocks.
- [Local inference](https://docs.syntax-ftc.com/docs/inference/local-inference): Running models on your own machine — GPU, Apple Silicon, or CPU.
- [Managed remote (dUX)](https://docs.syntax-ftc.com/docs/inference/managed-remote): dUX-backed cloud GPU. Pick a model, pick a tier, deploy. dUX handles placement, autoscaling, drivers, and ingress.
- [Multimodal capabilities](https://docs.syntax-ftc.com/docs/inference/multimodal): Image, video, audio, 3D, UI grounding, OCR, and time-series forecasting — all reachable through the same Bridge.
- [Inference overview](https://docs.syntax-ftc.com/docs/inference/overview): How Syntax serves models — local, remote self-hosted, managed remote on dUX, and hosted providers.
- [Remote self-hosted](https://docs.syntax-ftc.com/docs/inference/remote-self-hosted): Run models on your own remote box — your server, your GPU, your SSH — with Syntax handling the lifecycle.
- [How Syntax works](https://docs.syntax-ftc.com/docs/introduction/how-it-works): A high-level walkthrough of Syntax's three planes, the Bridge, and what happens to a request from your editor to a model and back.
- [What is Syntax?](https://docs.syntax-ftc.com/docs/introduction/what-is-syntax): Syntax is your fully managed, privately owned, general-purpose AI factory.
- [Why Syntax?](https://docs.syntax-ftc.com/docs/introduction/why-syntax): The reasons teams pick Syntax over rolling their own AI deployment stack.
- [Catalog overview](https://docs.syntax-ftc.com/docs/models/catalog-overview): Hundreds of models across many purposes, all reachable through the same Bridge.
- [Licensing & attribution](https://docs.syntax-ftc.com/docs/models/licensing): Every model in the catalog declares its license. Syntax surfaces it before you deploy and at runtime.
- [Modalities](https://docs.syntax-ftc.com/docs/models/modalities): Text, image, video, and audio — what each modality means in Syntax and how multimodal models surface to your harness.
- [Model purposes](https://docs.syntax-ftc.com/docs/models/purposes): The coarse classification Syntax uses to know how each model should be served.
- [Reasoning models](https://docs.syntax-ftc.com/docs/models/reasoning-models): How reasoning effort flows through Syntax — three distinct mechanisms behind one consistent control.
- [Tool use](https://docs.syntax-ftc.com/docs/models/tool-use): How tool calls work through Syntax — across providers, across engines, across model families.
- [Linux](https://docs.syntax-ftc.com/docs/platforms/linux): Platform notes for running Syntax on Linux.
- [macOS](https://docs.syntax-ftc.com/docs/platforms/macos): Platform notes for running Syntax on macOS.
- [Windows](https://docs.syntax-ftc.com/docs/platforms/windows): Platform notes for running Syntax on Windows.