# Wiggum CLI

> Wiggum is an open-source AI agent that plugs into any codebase — scans your tech stack, generates feature specs through AI-powered interviews, and runs autonomous coding loops (the Ralph loop technique) via Claude Code, Codex, or any CLI-based coding agent.

- Install: `npm install -g wiggum-cli`
- Source: https://github.com/federiconeri/wiggum-cli
- License: MIT + Commons Clause

## Pages

- [Homepage](https://wiggum.app): Product overview, how it works, capabilities, and FAQ
- [Blog](https://wiggum.app/blog): Technical blog about autonomous coding, spec generation, and the Ralph loop
- [Pricing](https://wiggum.app/pricing): Free tier (unlimited, self-hosted) and Pro/Team plans
- [Roadmap](https://wiggum.app/roadmap): Public roadmap with milestones, kanban board, and release history
- [Changelog](https://wiggum.app/changelog): Full release history from v0.9.0 to latest
- [Privacy Policy](https://wiggum.app/privacy): Privacy policy — no telemetry, no tracking in CLI
- [Terms of Service](https://wiggum.app/terms): Terms of service and license details

## Blog Posts

- [What Is Wiggum CLI?](https://wiggum.app/blog/what-is-wiggum-cli): Overview of the autonomous coding agent — scan, interview, execute
- [What Is the Ralph Loop?](https://wiggum.app/blog/what-is-the-ralph-loop): Deep dive into the Ralph loop methodology and how Wiggum implements it
- [Wiggum CLI vs Ralph Wiggum Bash Scripts](https://wiggum.app/blog/wiggum-vs-ralph-wiggum-scripts): Why spec generation matters and how Wiggum differs from simple bash loops

## How It Works

1. **Scan with `/init`** — Point Wiggum at any project and it auto-detects your tech stack, frameworks, languages, and conventions. Zero config.
2. **Interview with `/new`** — Describe what you want in plain English. Wiggum uses your codebase context to interview you and generate a detailed, implementation-ready spec.
3. **Execute with `/run`** — Hand the spec to your coding agent. The Ralph loop runs autonomous plan-implement-test-verify-PR cycles with progress checkpoints.

## Capabilities

- Stack scanning (shipped)
- AI-powered interviews (shipped)
- Spec generation (shipped)
- Ralph loop execution (shipped)
- TUI monitor (shipped)
- Claude Code support (shipped)
- Full phase observability (in progress)
- Review mode controls (in progress)
- Remote dashboard (planned)
- Push notifications (planned)
- Multi-CLI adapters (planned)
- Multi-agent orchestrator (planned)

## Full Content

For the complete content of all pages in markdown format, see [llms-full.txt](https://wiggum.app/llms-full.txt).