Skip to main content
Launch wiggum with no arguments to open the interactive terminal UI: 
wiggum
The TUI provides a persistent session with command autocomplete, live feedback, and a visual interface for every phase of feature development.

​
Available commands

CommandAliasDescription
/init/iScan project and configure AI provider
/new <name>/nCreate a feature spec via AI interview
/run <name>/rStart the autonomous coding loop
/monitor <name>/mMonitor a running feature
/sync/sRe-scan project and update context
/configManage API keys and settings
/help/hShow available commands
/exit/qExit wiggum
Press Esc to cancel any operation.

​
The interview flow

When you run /new <name>, wiggum starts a 4-phase AI interview:
1

Context

Share reference URLs, documentation, or files relevant to the feature.
2

Goals

Describe what you want to build in plain language.
3

Interview

The AI asks 3-5 clarifying questions to understand scope, edge cases, and constraints.
4

Generation

Wiggum produces a detailed feature spec saved to .ralph/specs/.

​
The run screen

When you run /run <name>, the TUI shows a live view of the autonomous loop:
  • Activity feed — real-time log of what the coding agent is doing
  • Diff stats — files changed, lines added and removed
  • Action inbox — review and approve AI decisions without breaking the loop
  • Run summary — final results when the loop completes

​
Spec autocomplete

When typing /run, wiggum autocompletes spec names based on the specs in your .ralph/specs/ directory.