←All work04 / 04
Ralph Wiggum
Runs Claude Code in a loop until the task is really done — a completion promise, not a guess.
- Year
- 2026
- Role
- Co-creator
- Stack
- Rust · Tokio · ratatui · crossterm · Claude Code CLI
Overview
Ralph Wiggum wraps the claude CLI and runs your prompt iteratively. Each round checks whether the previous one actually finished the job; the loop ends only when Claude emits an explicit completion promise.
My part
- 01Daily testing on real projects — reporting what was missing and what got in the way of letting the agent run on its own.
- 02Co-designed the loop prompts: the rules that tell the agent it may only promise completion once the work is verified.
- 03Ideas that shaped the roadmap, from iteration limits and resumable state to per-project configuration.
- 04Development itself happened on a teammate's machine — I focused on the product, the prompts and the feedback loop.
“Built at a time when AI agents still struggled to work autonomously — they'd stop halfway and declare victory. Ralph kept them honest.”
Highlights
- Min / max iterations, custom promises, resumable state and optional session continuation.
- Inline ratatui status bar, markdown rendering and coloured terminal output.
- Per-project .ralph.toml with prompt prefix, suffix and system prompt.
- Rust 2024 edition, async with Tokio.