Whitespace.
See who already built your idea — and the space they left open.

CLUSTER LOCAL-DESKTOP-INDEXES · 15 ENTRIES · EARLIEST ENTRY 2026-09-11

Local semantic desktop search

This cluster consists of desktop applications that index local files, code, and notes to answer natural-language questions with traceable citations, with a strong emphasis on privacy and on-device processing. The dated history is too thin to read a shape from — only one entry predates the index start — so the cluster likely predates the index or its members are mostly undated. Among the named traction leaders, unbury shows the strongest activity signal with 3 stars, ahead of local-file-rag and langolier at 2 stars each.

Entry timeline

ENTRY TIMELINE

NOV 2024: 1MAY 2026: 1AUG 2026: 1SEP 2026: 10OCT 2026: 2
NOV 2024OCT 2026

Each bar is the month a member carries, which is a creation date where the source published one and a crawl date otherwise. Nothing in the index was found before 11 August 2026, and coverage broadened sharply on 14–15 August, so a bar from then on reports how much we found that month, not how much was built; an earlier bar reports how far back a member's own source dated it — not how long we have been watching.

Members by activity

Activity signals, not revenue.

Build origin · 2 ai-built · 13 unlabelled

Operator · 7 hobby · 1 indie · 1 commercial · 1 open source · 5 unlabelled

Two labels per entry, never collapsed into one: how it was built, and who stands behind it. Counted over the 15 listed below. Unlabelled means nothing has decided yet — not that the answer is small.

  1. 01jev-rag6★15 dayslivehobbyLocal knowledge search app that indexes local files and answers questions with cited, grounded streaming replies using retrieval and reranking.
  2. 02MeiliOps1★15 daysliveindieDesktop admin app for a search engine server that lets users browse documents, adjust settings, track indexing tasks, and run local instances.
  3. 03langolier2★25 daysliveDesktop app that indexes local documents, code, and notes to answer questions with citations from local or cloud AI models.
  4. 04bearing-diligence-oss0★13 days—Desktop app for people following local government meetings that reads public records, highlights changes between packets, and answers questions with cited passages.
  5. 05redrob-recall0★27 dayslivecommercialDesktop app that indexes local files for semantic search and answers questions with cited excerpts while keeping everything on-device.
  6. 06llmsearch-mobile0★16 days—Mobile app that searches a personal index with cited AI answers, searches the web, and crawls sites from a phone.
  7. 07folio-bookshelf0★12 days—ai-builthobbyDesktop app that stores files and web links in a personal searchable bookshelf for reading and managing important documents locally.
  8. 08recall0★23 days—Desktop search app that indexes personal files and finds answers on the user's device while keeping data local.
  9. 09smartseacrch0★18 days—Desktop app that answers questions about local manuals and documents by searching selected folders and showing the source passage.
  10. 10pocket-RAG0★27 dayslivehobbyPrivacy-focused desktop app that indexes local documents and answers questions in plain language with traceable citations.
  11. 11callRoot0★1 mo—hobbyDesktop app that indexes local documents and provides real-time search with folder watching and no cloud telemetry.
  12. 12local-knowledge-hub0★1 mo—hobbyLocal-first knowledge base web app that imports documents, performs hybrid search, and answers questions via AI while keeping data in SQLite.
  13. 13session-search0★1 mo—hobbyDesktop search app that indexes local text and supports quoted-phrase queries, favorites, and fully offline use.
  14. 14know-your-files2★4 mo—ai-builthobbyDesktop app that adds an AI-assisted metadata sidebar for browsing, summarizing, and searching local documents on Windows.
  15. 15RecollDroid0★1 yrabandonedliveopen sourceMobile front end for a self-hosted full-text search engine that indexes and searches desktop or server files remotely.

Ranked by traction, highest first, and paged 20 at a time — this is a window on the cluster, never the whole of it. Ties are broken by a stable id so a product cannot appear on two pages or fall between them. Browse every cluster.