# Luxe

> A coding agent for your terminal: write, review and ship code in one workflow, with Guided Review, Git and GitHub, and any model.

Every page is plain markdown. The whole guide in one file: https://luxe.dev/llms-full.txt

## Get started

- [Overview](https://luxe.dev/docs/index.md): What Luxe is, and where to find what you need.
- [Install](https://luxe.dev/docs/install.md): Install Luxe, check your setup, and pick a font.
- [Quickstart](https://luxe.dev/docs/quickstart.md): From first launch to a reviewed pull request.

## Using Luxe

- [The interface](https://luxe.dev/docs/interface.md): The start screen, the conversation, the composer, the dock, the statusline and the preview.
- [Commands and keys](https://luxe.dev/docs/commands.md): The Command Palette, slash commands, Help, every default key, and how to rebind them.
- [Mentions](https://luxe.dev/docs/mentions.md): Point the agent at a file, skill, issue, MCP server or your own tracker with `@`.
- [Guided Review](https://luxe.dev/docs/guided-review.md): Read a change chapter by chapter, comment for the agent, and finish with a commit, fixes or a pull request.
- [Git and GitHub](https://luxe.dev/docs/github.md): Worktrees, issues, opening and merging pull requests, review threads, and stacks.
- [Sessions and context](https://luxe.dev/docs/sessions.md): Resume past sessions, see what fills the context window, and how Luxe keeps long sessions going.
- [Models and providers](https://luxe.dev/docs/providers.md): Sign in to a provider, choose a model and thinking level, and run local models.
- [Tools](https://luxe.dev/docs/tools.md): What the agent can use: files, the shell, tests, Git, code intelligence, a debugger and the web.
- [How the agent works](https://luxe.dev/docs/agent.md): How the agent writes to you, asks you questions, plans, and gets a second opinion.
- [Autonomous runs](https://luxe.dev/docs/loop.md): Let the agent work through a phased plan on its own, with tests and a reviewer at each phase.

## Customize

- [Configuration](https://luxe.dev/docs/configuration.md): Where Luxe's files live, what a project can set, and every key in config.json.
- [Appearance](https://luxe.dev/docs/appearance.md): Themes, the statusline, icons and fonts, the conversation's layout, diffs and images.
- [Project context](https://luxe.dev/docs/project-context.md): Give the agent your project's conventions in AGENTS.md, and how Luxe finds the project.

## Extend

- [Extending Luxe](https://luxe.dev/docs/extending.md): Which kind of extension you need, how to install one, and what stays stable across updates.
- [Skills](https://luxe.dev/docs/skills.md): Teach the agent a procedure it loads only when it needs it.
- [MCP servers](https://luxe.dev/docs/mcp.md): Give the agent tools from MCP servers: add one, sign in, and control what it may do.
- [Mention sources](https://luxe.dev/docs/mention-sources.md): Add your own tab to the @ picker: Jira issues, Asana tasks, anything a program can list.
- [Hooks](https://luxe.dev/docs/hooks.md): Run your own commands at points in a turn: block, rewrite or audit tool calls, and add context.
- [Custom providers](https://luxe.dev/docs/custom-providers.md): Connect any endpoint, and set a model's context window, thinking levels, request format and samplers.
- [The RPC protocol](https://luxe.dev/docs/rpc.md): Drive Luxe from your own program: an editor plugin, a dashboard, or a front end of your own.
- [Recipes](https://luxe.dev/docs/recipes.md): Extensions put together: Asana, subagents, a classifier guard, Herdr, and a local model.

## Reference

- [Security and permissions](https://luxe.dev/docs/security.md): What the agent may do, the rules and prompts that decide it, secrets, and what Luxe sends over the network.
- [Command line](https://luxe.dev/docs/cli.md): Every luxe command and flag.
- [Environment variables](https://luxe.dev/docs/environment.md): The environment variables you can set, and the ones Luxe sets.
- [Troubleshooting](https://luxe.dev/docs/troubleshooting.md): Common problems, where Luxe logs, and what to include in a bug report.