vercel-labs/ralph-loop-agent

Continuous Autonomy for the AI SDK

About the project

ralph-loop-agent is an experimental framework for running AI SDK agents in repeated work-and-check cycles until a task meets its completion conditions. It is for developers who need agents to verify results, receive feedback, and continue iterating on complex tasks. The catalogue instruction supports using this continuous autonomy workflow.

These files are vercel-labs/ralph-loop-agent's own configuration. They tell Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.

830Stars on the repository
1Files it configures its agents with
532Tokens loaded in every session
2Agents configured

Instructions