ralph

Type `ralph "prompt"` to start open code in a ralph loop. Also supports a prompt file & status check. Open Code, Claude Code, Codex, Copilot

A curated list of resources about Ralph, the AI coding technique that runs AI coding agents in automated loops until specifications are fulfilled.

A better /goal

Unified AI Development Framework - BMAD phases with Ralph execution loop

Gemini CLI extension for Ralph loops

A long-running AI agent loop. Ralph automates software development tasks by iteratively working through a task list until completion.

The Ultimate AI-powered app for consultants worldwide (EY, Deloitte, PwC, KPMG, McKinsey, BCG, Bain, etc) to do their research and complete work in hours instead of days, weeks and months.

Copilot implementation of Ralph loop

Ralph is a small runner around GitHub Copilot CLI (standalone) inspired by the“Ralph Wiggum” technique: run a coding agent from a clean slate, over and over, until a stop condition is met

Ralph is a Lisp-1 dialect that compiles to JavaScript

Educational autonomous-agent loop runtime. Not actively maintained.

Pure bash loop Ralph running in isolated Sprites.

Autonomous ML agent for running experiments using Claude.

A Pi extension command that executes raw user intent to completion with strict, verifiable termination. `/until-done` runs until a truthful terminal state: 1) all criteria are objectively satisfied or 2) cannot proceed safely, deterministically, or verifiably. It never stops based on perceived completion or invents success.

Get started with THE bash script for running unsupervised agentic coding loops

A ralph harness for long-running AI coding tasks — a generator-evaluator loop that orchestrates Claude Code, OpenAI Codex & GitHub Copilot across repositories 🍩

A high-performance implementation of the Ralph autonomous loop. Orchestrates multi-agent execution across Claude Code and Cursor, utilizing Git worktree isolation to scale PRD-driven development.

Autonomous issue resolver

A simple way to run autonomous AI agent tasks. Copy this into any project, define what you want done in markdown, and let the AI do the work.

Autonomous AI agent loop that keeps working through your project while you keep planning what comes next.