> ## Documentation Index
> Fetch the complete documentation index at: https://wiggum.app/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> Wiggum is an AI agent that plugs into any codebase and ships features autonomously.

Wiggum scans your project, generates detailed specs through an AI-guided interview, and delegates coding to an autonomous implement-test-fix loop. No configuration, no boilerplate.

<Steps>
  <Step title="Scan">
    Wiggum auto-detects 80+ technologies in your stack — frameworks, databases, testing tools, deployment targets, and more.
  </Step>

  <Step title="Spec">
    An AI-guided interview produces a detailed, project-aware feature specification.
  </Step>

  <Step title="Loop">
    Wiggum hands the spec to a coding agent and runs autonomous implement → test → fix cycles until the feature ships.
  </Step>
</Steps>

## Two ways to use wiggum

<CardGroup cols={2}>
  <Card title="Interactive mode" icon="terminal" href="/using-wiggum/interactive-mode">
    Launch the terminal UI and work through commands interactively. The recommended way for most developers.
  </Card>

  <Card title="Headless mode" icon="code" href="/using-wiggum/headless-mode">
    Run commands directly from your shell. Useful for CI pipelines, scripting, and integration with other agents.
  </Card>
</CardGroup>

## Get started

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Install wiggum and ship your first feature in 5 minutes.
  </Card>

  <Card title="Commands" icon="list" href="/commands/init">
    Full reference for every wiggum command.
  </Card>
</CardGroup>