I built a pipeline in a single session that consolidates the 58 tech-blog articles of my service Kotonia (ja/en/zh) into a semantic index, then uses that index to detect duplicates for new article mining. Raw articles → semantic index → TF-IDF dedup → chunked draft generation — full path running...
Source: [Dev.to](https://dev.to/shinji_shimizu_bb51276a5e/implementing-claude-codes-memory-model-as-a-dreaming-layer-on-58-articles-3g2l)