Tweet Index
Find the post you meant to come back to.
My roleCreator · built with Claude
01 / The context
A problem worth exploring.
Saving is easy. Finding the right post months later is harder, especially when the useful idea is inside an image or a linked article.
A local search tool for saved X likes and bookmarks, with meaning-based retrieval and model-assisted ranking.
02 / Inside the project
See how it works.
Choose a step, inspect the details, and explore the thinking behind the experience.
03 / Decisions & evidence
Behind the experience.
Approach & boundaries
Five stages—Capture, Store, Enrich, Index, and Search—turn saved posts into searchable results. SQLite and embeddings are local; model enrichment and reranking send relevant content to API providers. Linked pages and images are fetched during enrichment.
What the evidence shows
The original recording shows one search run, including timing and cost. Its counts and measurements describe that recording, not guaranteed product performance.
Sources & attribution
Reviewed against the linked public sources and supplied assets. Demonstrations on this page use fixed example content unless labeled as an original recording or screenshot.