This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady.
What I Built
Little Pile helps with a list of loose notes. Paste one note per line and it suggests small groups based on meaning. Each group takes its name from an original note. Nothing is thrown away: review the groups, keep a note separate, or ungroup the whole pile. Then download a Markdown copy.
It handles up to 40 short notes. It does not open pasted links, sort your actual files or touch your inbox.
Demo
https://itsdanielsultan.github.io/little-pile/
Code
https://github.com/itsdanielsultan/little-pile
How I Built It
A small open model, MiniLM, reads the notes in a browser Worker. Its sentence embeddings help the app find related lines, even when they use different words. The model version is pinned, and the grouping and export steps are ordinary code.
The suggestions can be wrong. There are review controls instead of automatic deletion. AI tools generated the implementation and this write-up; checks used synthetic notes.
Why Does Open Innovation Matter?
The open model can run on your device, so sorting does not need to send your notes to a hosted model or charge for each request. First use downloads public model files; those hosts still see normal connection details. Notes stay in page memory and clear on reload. Offline reload is not promised.
The model, grouping rule and export code can be inspected and changed.
Prize Categories
Overall prize only.
Top comments (0)