LLM Wiki
A cross-platform desktop application that has a language model read imported documents and incrementally build and maintain a structured, interlinked wiki, instead of answering from scratch with retrieval-augmented generation each time.
LLM Wiki is a personal knowledge base that builds itself: a language model reads imported documents, generates wiki pages with source traceability, and keeps the wiki current as more material is added, instead of doing retrieve-and-answer style search on every question.
It ingests PDF, Office documents, EPUB and MOBI files, Org mode files, images, media, web clips and batches of URLs, with built-in, cloud or local PDF processing, and extracts and captions embedded images with a vision model. A knowledge graph links pages by direct links, source overlap, similarity and type affinity, with community detection surfacing knowledge clusters, and vector semantic search runs against any OpenAI-compatible embedding endpoint.
A Rust backend chat agent answers questions using the wiki, sources, graph and web retrieval, can generate workspace files, and supports local Agent Skills. A deep research mode runs multi-query web searches and ingests the results into the wiki.