Local Semantic Search for Notes

Semantic search over local notes, PDFs, and images on CPU, no cloud upload

Problem

Knowledge workers accumulate local notes, PDFs, and images, but keyword search fails to find semantically relevant content. Cloud semantic search raises privacy concerns. A recent HN Show HN demonstrated CPU-based semantic search, proving lightweight local cross-modal search is feasible but not yet user-friendly.

Solution

A local desktop app that indexes text, PDFs, and images (via OCR/CLIP) in chosen folders, offers natural language queries, and returns the most relevant snippets and files. All computation runs on local CPU without GPU or network.

Users

Researchers, lawyers, doctors, and other professionals handling large local document sets, plus privacy-focused individuals.

MVP

Choose folders and build index; support mixed search across text, PDF, and images; natural language queries; highlight and jump to results; incremental index updates.

Revenue

One-time purchase plus subscription for advanced features (multi-device sync, team-shared indexes).

Why now

Lightweight embedding models and vector stores now run smoothly on CPU, and demand for local, privacy-first search is growing; indie developers can avoid competing head-on with cloud giants.