# System-1 Gateway > Fast multiple-choice decisions for Claude Code and other MCP clients, from a local engine you pick. Every page has a Markdown copy at its address with .md in place of .html. The whole site as one file: llms-full.txt. ## Home - [Home](https://thematthub.github.io/Sys1-AI-Gateway/index.html): The System-1 Gateway gives Claude Code fast multiple-choice decisions from a small local engine, through one MCP server with three stable tools. ## Tutorial - [Your first decision](https://thematthub.github.io/Sys1-AI-Gateway/tutorial/first-decision.html): This tutorial takes you from nothing to one `system1_decide` call in Claude Code, in about five minutes plus the engine download. ## How-to - [Install the gateway](https://thematthub.github.io/Sys1-AI-Gateway/how-to/install.html): The gateway installs either as a Claude Code plugin with guided setup or with one script from a clone. - [Install an engine](https://thematthub.github.io/Sys1-AI-Gateway/how-to/engines.html): An engine is the local model that actually answers; the gateway only talks to it. - [Configure](https://thematthub.github.io/Sys1-AI-Gateway/how-to/configure.html): The gateway reads one TOML file, and every key in it is optional. - [Turn on model routing](https://thematthub.github.io/Sys1-AI-Gateway/how-to/routing.html): Model routing lets System-1 suggest a Claude model (haiku, sonnet or opus) for the subagents Claude spawns. - [Calibrate and evaluate](https://thematthub.github.io/Sys1-AI-Gateway/how-to/calibrate.html): Calibration makes an engine's confidence mean what it says, so that `min_confidence` is a real threshold. - [Add a provider](https://thematthub.github.io/Sys1-AI-Gateway/how-to/add-provider.html): A provider is one small adapter file that maps the gateway's neutral request to one engine's API. - [Troubleshoot](https://thematthub.github.io/Sys1-AI-Gateway/how-to/troubleshoot.html): When the gateway misbehaves, check one layer at a time from the top and stop at the first that fails. ## Reference - [Tools and schema](https://thematthub.github.io/Sys1-AI-Gateway/reference/tools.html): The gateway exposes three MCP tools over stdio, and their contract is schema version `"1"`. - [Config keys](https://thematthub.github.io/Sys1-AI-Gateway/reference/config.html): The config file is `%APPDATA%\system1\config.toml` on Windows and `~/.config/system1/config.toml` (or `$XDG_CONFIG_HOME/system1/config.toml`) on Linux and macOS, or the path in `SYSTEM1_CONFIG`. - [Slash commands and scripts](https://thematthub.github.io/Sys1-AI-Gateway/reference/commands.html): The plugin adds seven slash commands to Claude Code, and each one drives scripts that you can also run yourself with the gateway venv Python. - [Providers](https://thematthub.github.io/Sys1-AI-Gateway/reference/providers.html): A provider is the adapter between the gateway and one engine, and six are built in: `laya`, `von`, `systemone`, `ollama`, `anthropic` and `mock`. ## Background - [What System-1 means here](https://thematthub.github.io/Sys1-AI-Gateway/background/system-1.html): The name comes from Daniel Kahneman's *Thinking, Fast and Slow*: System 1 is fast and intuitive, System 2 slow and deliberate. - [How routing and calibration work](https://thematthub.github.io/Sys1-AI-Gateway/background/routing-and-calibration.html): Routing and calibration share one idea: ask the engine what it can see in the text, and trust its answer only as far as measurement shows. ## Studies - [Which model for naga decisions](https://thematthub.github.io/Sys1-AI-Gateway/studies/naga-decisions.html): An assistant that drives the naga simulation engine must pick one of 90 agent tools for each step, and this study measures which small or cheap model picks best, and how fast. - [Which model tier for a Claude Code task](https://thematthub.github.io/Sys1-AI-Gateway/studies/claude-code-routing.html): This study asks whether a System-1 engine can pick the Claude model a subagent task needs, and finds that asking it directly works on easy synthetic prompts and failed on real work. ## Release notes - [Release notes](https://thematthub.github.io/Sys1-AI-Gateway/release-notes.html): Releases are tagged `system1--v`, the Claude Code plugin convention (`claude plugin tag . --push`), and listed on GitHub.