Ralph is an autonomous AI agent loop that runs repeatedly until all PRD items are complete.
Repository Index
132,241 visible repositories in the index
1–13 of 13 · Most stars
Keep searching, reading webpages, reasoning until it finds the answer (or exceeding the token budget)
- deepresearch
- deepsearch
The meta-skill that improves your skills, including itself. Turns the corrections, judgement calls and repeated workflows of your sessions (autonomous or human-led) into small skill updates and new skill candidates, each with its evidence and reason. Nothing touches a skill until you approve it. Augmented Expertise in practice. CC BY 4.0.
Qiushi-Skill: Build agents that investigate first, focus on the main contradiction, validate in practice, and keep pushing until the work is actually done. 求是Skill——从经典唯物辩证法与实践哲学中提炼出一条总原则和九大方法论工具武装AI大脑。
My Ralph Wiggum setup, an autonomous bash script that runs Claude Code, Codex, OpenCode, Cursor agent, Qwen & Droid in a loop until your PRD is complete.
- claude-code
- opencode
- ralph-loop
- ralph-wiggum
Build a system, load it until it breaks, and watch why. A system design simulator for learning distributed systems.
Claude Code / Cowork skill: interview the user relentlessly until reaching shared understanding
turn old phones into ai agents - give it a goal in plain english. it reads the screen, thinks about what to do, taps and types via adb, and repeats until the job is done.
Turn any goal into a short prompt that makes your agent set a real quality bar, run builder and critic pairs, compare blind, and loop until it wins.
CodeAgent is an open-source coding agent that lives in your terminal. It understands your repository, plans multi-step changes, writes and edits files, runs commands and tests, and iterates until the task is done — all with a transparent, extensible tool loop.
A curated list of resources about Ralph, the AI coding technique that runs AI coding agents in automated loops until specifications are fulfilled.
- ai-coding
- ralph
- ralph-loop
- ralph-wiggum
A framework for building decision-model harnesses for any kind of task. Your program offers the model a short list of next steps, and the model picks one at a time until it can answer.
- classifiers
- decision-models
- evals
- llm-harness
Agent skill: examine a product you're authorised to rebuild, build your own, then test against the original and fix gaps until every must-have on a written checklist passes. Inspired by REA (@morluto), not affiliated. MIT.