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

CLUSTER DESKTOP-LOCALLY-QUESTIONS · 4 ENTRIES · EARLIEST ENTRY 2023-11-01

Local AI document Q&A apps

These are desktop or terminal applications that run a local AI model to answer questions, often drawing from the user's own documents, with an emphasis on privacy. The cluster's dated history is too thin to read a shape from -- it predates the index or its members are undated. Among the traction leaders, mybutler has 22 stars, followed by local-rag-agent (1 star) and anything-llm (0 stars).

Entry timeline

ENTRY TIMELINE

NOV 2023: 2AUG 2026: 1OCT 2026: 1
NOV 2023OCT 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 · 4 unlabelled

Operator · 1 hobby · 2 open source · 1 unlabelled

Two labels per entry, never collapsed into one: how it was built, and who stands behind it. Counted over the 4 listed below. Unlabelled means nothing has decided yet — not that the answer is small.

  1. 01test_rag0★11 days—hobbyDocument question-answering application that lets users chat with their own documents using a local AI model and isolated data.
  2. 02chatd0★1 yrabandonedliveopen sourceDesktop application that lets users ask questions and converse with their own documents using a locally run AI model.
  3. 03chatd-bin0★1 yrabandonedliveopen sourceDesktop application that lets users ask questions and converse with their own documents using a locally run AI model.
  4. 04Bavarder0★unknownliveDesktop application that lets users pose questions to a locally running AI assistant and receive responses directly on their computer.

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.