Working on something in public! I call it Open Reverie. It's a place for your reveries. A companion agent harness with hierarchical tiered memory so it remembers a lot of what you've shared, and helps you reflect on it, come back to things, and build a graph of your thoughts.

This was thought of as an extension to Ruminate a few months ago, and as the librarian in Murmur, but now it's also an open source harness for anyone to use.

Would love code & idea contributions from people!

Debugging code is like being a detective in a crime movie where you're also the murderer.

/ralph-wiggum:ralph-loop combined with /speckit.implement is a game changer. Especially after launching claude with --dangerously-skip-permissions.

Use Speckit's specify, clarify, plan, and tasks to provide all required context and acceptance criteria for the story. Ensure the implementation plan uses well-parallelized sub-agent spawning as the execution mechanism.

The ralph-loop then drives execution, recursively enforcing the spec and iterating on the workflow until everything is dialed in and correct.

Or just /ralph-loop in Claude Code.

/ralph-loop "<prompt>" --max-iterations <n> --completion-promise "<text>"

🚀

while :; do cat prompt.md | claude -p --dangerously-skip-permissions; done

Works remarkably well when prompt contains proper boundary and output necessary conditions and it gives some information to the agent about storing memory in a file.

AI coding tools are the new LEGO for adults. They are so much fun, and have truly shortened the gratification loop for hobby projects!