ralph-wiggum

Automate iterative development loops with file-persisted state and context rotations.

496|65|Updated Jan 4, 2026

Search Tags:#automation #git #guardrails #cursor #context-management #ralph #autonomous-iteration

Ready to run

npx skills add https://github.com/agrimsingh/ralph-wiggum-cursor --skill ralph-wiggum-agrimsingh

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ralph-wiggum
Source: https://github.com/agrimsingh/ralph-wiggum-cursor/tree/main
Command: npx skills add https://github.com/agrimsingh/ralph-wiggum-cursor --skill ralph-wiggum-agrimsingh

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires jq, git, cursor-agent, gum, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

Ralph Wiggum enables autonomous AI development by treating the LLM's contextual window as memory and by persisting state in files and git, preventing context pollution and enabling fresh-context rotations when necessary.

Core Features & Use Cases

State persistence: state and progress are stored in .ralph, ensuring continuity across iterations without relying on the model's memory.
Guardrails and learning: uses "Signs" (guardrails) to capture lessons from failures and guide future iterations.
Context management: detects gutter scenarios, manages context health, and rotates context to avoid memory pollution.
Git-backed memory: state is committed to git, enabling reproducible progress and clean handoffs.
Parallel execution: supports isolated worktrees for parallel task processing and integrated merges.
USB of automation: designed to coordinate task definitions (RALPH_TASK.md) with automated iteration loops.

Quick Start

Create a RALPH_TASK.md at the project root and run ./scripts/ralph-setup.sh to start the interactive loop.

Frequently Asked Questions about ralph-wiggum

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I automate autonomous iteration in Cursor without context pollution?▼

Autonomous iteration in Cursor without context pollution is achieved by using a Ralph loop to repeatedly feed prompts while persisting state in files. This approach manages context health and rotates fresh context to prevent memory pollution across greenfield tasks.

What is context budgeting and how does it work with autonomous AI development?▼

Context budgeting in autonomous AI development detects gutter scenarios and manages context health by rotating fresh context. It treats the LLM contextual window as memory, preventing pollution by persisting state in files and git instead of relying on the model memory.

How do I set up autonomous iterative development with git-backed memory?▼

To set up autonomous iterative development with git-backed memory, create a RALPH_TASK.md task definition at your project root and run the setup script. This starts an interactive loop that persists state and progress in a dedicated directory, ensuring continuity across iterations.

Does autonomous iteration work with parallel task processing in git worktrees?▼

Autonomous iteration works with parallel task processing by using isolated git worktrees. It supports parallel task processing and integrated merges, allowing multiple automated iteration loops to run concurrently while maintaining separate state persistence.

Do I need jq and gum to run autonomous iteration loops?▼

Yes, you need jq, gum, git, and cursor-agent installed to run autonomous iteration loops. These dependencies support the interactive loop, state persistence, git-backed memory, and context management features required for the workflow.

Why should I use guardrails for automated AI development workflows?▼

Guardrails should be used for automated AI development workflows to capture lessons from failures and guide future iterations. These Signs prevent repeated errors by enforcing constraints that shape the autonomous iteration loop toward successful task completion.