snarktank/ralph
- Source
- GitHub
- First trending
- Category
- Agents
- GitHub stars
- 21,802
- Main language
- TypeScript
This page introduces an external open-source repository. It is not an HDATF product.

What it does
Ralph runs Amp or Claude Code in a loop until every item in a PRD (product requirements document) is done. Each run starts with fresh context, and memory persists in git history, progress.txt and prd.json.
How it helps ATF
Keeping memory in files and git between fresh runs is worth comparing with how Harness keeps goal, state and memory for one task while handing work to executors such as Claude Code.
License
MIT Permissive. Commercial use and changes are allowed if the copyright notice is kept.
More in this category
- eigent-ai/eigent
An open-source desktop app built on CAMEL-AI that runs multiple AI agents in parallel on workflows, or one meta agent on a focused task. It supports local deployment, a choice of models, MCP, skills, and browser and terminal tools. - virattt/dexter
Dexter is a financial research agent that breaks a question into research steps, gathers live market data with tools, and checks and refines its own work before answering. It is meant for learning, not real trading or investment. - iOfficeAI/AionUi
A Cowork app where AI agents read files, write code, browse the web and automate tasks on the user's computer. It works with many CLI agents such as Claude Code, Codex and Hermes, with remote access and scheduled runs. - MiroMindAI/MiroThinker
MiroThinker is a deep research agent, with released models, built for complex research and prediction tasks. The project includes benchmark evaluation and trace collection, and its online version generates research reports that can be previewed and shared. - frankbria/ralph-claude-code
A tool that runs Claude Code in a loop to keep improving a project until complete. It exits only when completion indicators and an explicit exit signal both appear, and uses rate limits and a circuit breaker.
Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.