hmeng
(Haris M)
January 1, 2026, 8:11am
1
Feature request for product/service
Cursor IDE
Describe the request
Could we get some form of ralph / loop until it’s done version in cursor?
# Ralph Wiggum Plugin
Implementation of the Ralph Wiggum technique for iterative, self-referential AI development loops in Claude Code.
## What is Ralph?
Ralph is a development methodology based on continuous AI agent loops. As Geoffrey Huntley describes it: **"Ralph is a Bash loop"** - a simple `while true` that repeatedly feeds an AI agent a prompt file, allowing it to iteratively improve its work until completion.
The technique is named after Ralph Wiggum from The Simpsons, embodying the philosophy of persistent iteration despite setbacks.
### Core Concept
This plugin implements Ralph using a **Stop hook** that intercepts Claude's exit attempts:
```bash
# You run ONCE:
/ralph-loop "Your task description" --completion-promise "DONE"
# Then Claude Code automatically:
# 1. Works on the task
This file has been truncated. show original
Operating System (if it applies)
MacOS
Artemonim
(Artemonim)
January 1, 2026, 8:24am
2
You could create a huge TODO.md file right now and ask Agent to complete all the tasks in it.
But that wouldn’t be economically efficient. At least until Context_summarize_tool is implemented.
And also, Cursor has a limit of 2 hours for working on a single request, yes.
jonbride
(Jonathan Bride)
January 7, 2026, 11:44am
4
I haven’t tested this, but someone has implemented their own Cursor version of the Ralph method:
Cursor CLI implementation of Geoffrey Huntley's Ralph Wiggum autonomous iteration technique with deliberate context management
Agree this would be helpful. The first step would need to be something that looks a lot like Plan mode, but decomposes large work into a lot of small tasks.
I’m testing Claude and just discovered this tool they have. A better implementation in Cursor would be amazing. I like Cursor’s ease of use but it feels like it’s spending it’s energy in the wrong directions. Ralph Wiggum with good context management, subagents and good prompts would be the right direction I think.
I’ve been using that Cursor CLI based harness for a day or two now and it’s awesome . Cursor should definitely integrate this as a stock feature, especially for larger plans.
Got mine to work on Cursor.
Contribute to flourishprosper/ralph-main development by creating an account on GitHub.
Use with caution. I have tested it on one of my features of an app i am developing and it worked through 15 user stories on 5 iterations.
it works, at least on linux it does, I cant get it it to work on WSL.