Skip to content
RALPH LOOP

Support

The ralph.sh script is designed to be hackable. It is configured to use Claude Code in Docker Sandboxes by default, and you can select another supported agent with --agent. Each run uses a deterministic sandbox name in the form ralph-<agent>-<current-dir>-<hash8>, so different agents get separate sandboxes for the same project. On exit or double Ctrl+C, Ralph stops only the named sandbox for the current invocation.

NB: skills are supported by all major agentic AI CLIs via symlinks.

Ralph uses semantic tags to communicate status:

  • <promise>COMPLETE</promise> - All tasks finished successfully
  • <promise>BLOCKED:reason</promise> - Agent needs human help
  • <promise>DECIDE:question</promise> - Agent needs a decision
CodeMeaning
0COMPLETE - All tasks finished
1MAX_ITERATIONS - Reached limit
2BLOCKED - Needs human help
3DECIDE - Needs human decision