A visual Kanban UI for autonomous AI coding with Claude Code
npm install ralph-wiggum-uiA visual Kanban UI for autonomous AI coding with Claude Code.
Ralph Wiggum UI helps you manage coding tasks that Claude Code executes autonomously. Add tasks to your backlog, and let Claude work through them one by one - or enable "AFK Mode" to run multiple tasks while you're away.
``bashIn any coding project
npx ralph-wiggum-ui init
Requirements
- Node.js 18+
- Claude Code CLI installed and authenticated
- Git initialized in your project
Commands
$3
`bash
npx ralph-wiggum-ui init
`Creates a
.ralph-wiggum-ui/ folder in your project with:
- config.json - Project configuration
- prd.json - Task list (PRD = Product Requirements Document)
- prompt.md - Instructions for Claude
- AGENTS.md - Project guide for AI agents
- progress.txt - Learning log across iterations
- logs/ - Execution logs$3
`bash
npx ralph-wiggum-ui
or
npx ralph-wiggum-ui serve
`Opens a Kanban board at
http://localhost:3210 where you can:
- Drag and drop tasks between columns
- Add new tasks
- View real-time logs
- Start single tasks or AFK mode$3
`bash
Interactive mode
npx ralph-wiggum-ui addQuick add
npx ralph-wiggum-ui add "Implement user authentication"With description and criteria
npx ralph-wiggum-ui add "Add dark mode" \
--description "Add a theme toggle to the settings page" \
--criteria "Toggle persists across sessions" \
--criteria "Respects system preference"
`$3
`bash
Run the next pending task
npx ralph-wiggum-ui runRun next 3 tasks
npx ralph-wiggum-ui run 3AFK Mode - run all pending tasks
npx ralph-wiggum-ui run --allContinue even if a task fails
npx ralph-wiggum-ui run --all --no-stop-on-failure
`$3
`bash
npx ralph-wiggum-ui status
`$3
`bash
All tasks
npx ralph-wiggum-ui listFilter by status
npx ralph-wiggum-ui list --status pending
npx ralph-wiggum-ui list --status completed
`How It Works
1. Add tasks to your backlog via CLI or web UI
2. Run starts Claude Code with your project context
3. Claude reads the task from
prd.json and implements it
4. When done, Claude outputs
5. The task is marked complete and the next one begins (in AFK mode)$3
A task is considered complete when:
- Claude outputs the completion tag:
- The process exits successfully$3
After each task, Claude appends learnings to
progress.txt. This file persists patterns and gotchas discovered during implementation, helping future iterations avoid the same mistakes.Project Structure
`
your-project/
├── .ralph-wiggum-ui/
│ ├── config.json # Project settings
│ ├── prd.json # Task list
│ ├── prompt.md # Claude instructions
│ ├── AGENTS.md # Project guide
│ ├── progress.txt # Learnings log
│ └── logs/ # Execution logs
│ └── US-001_2024-01-15T10-30-00.log
└── ... your code
`Configuration
Edit
.ralph-wiggum-ui/config.json:`json
{
"version": "1.0.0",
"project": "my-app",
"sourceDir": "src",
"commands": {
"test": "npm test",
"build": "npm run build",
"typecheck": "npm run typecheck"
},
"claude": {
"model": "opus"
},
"afk": {
"stopOnFailure": true,
"notifications": true
},
"logs": {
"retention": 50
}
}
`Works With Any Language
Ralph Wiggum UI works with any coding project - not just JavaScript/TypeScript. Use it with:
- Python
- Go
- Rust
- Ruby
- Java
- Or any other language
Just configure the appropriate test/build commands in your
config.json.Web UI Features
- Kanban Board: Drag tasks between Backlog, In Progress, and Completed
- Real-time Logs: Watch Claude's output as it works
- AFK Mode: Run all pending tasks with one click
- Live Progress: See which task is running and how many are complete
Tips
1. Write clear tasks: Include specific acceptance criteria
2. Keep tasks small: One feature or fix per task
3. Check progress.txt: Review learnings before adding similar tasks
4. Use AFK mode wisely: Start with a few tasks to verify quality
Troubleshooting
$3
Make sure Claude Code CLI is installed:
`bash
claude --version
`$3
Initialize git in your project:
`bash
git init
`$3
Check the logs in
.ralph-wiggum-ui/logs/` to see what went wrong. You may need to:MIT