Skip to main content

Prerequisites

Install

Ship a feature

1

Launch wiggum

Open the interactive TUI by running wiggum with no arguments:
2

Scan your project

Run /init in the TUI. Wiggum detects your tech stack and generates configuration in a .ralph/ directory.
You’ll be prompted to select your AI provider and enter your API key.
3

Create a feature spec

Run /new with a feature name. Wiggum starts an AI-guided interview to understand what you want to build.
Answer 3-5 questions about your feature. Wiggum generates a detailed spec in .ralph/specs/.
4

Run the autonomous loop

Run /run with the feature name. Wiggum delegates to your coding agent and runs implement → test → fix cycles.
The loop runs until all tests pass or it reaches the maximum iterations.

What’s next