# nashsu/llm_wiki

LLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base — automatically. Instead of traditional RAG (retrieve-and-answer from scratch every time), the LLM incrementally builds and maintains a persistent wiki from your sources。

Repository: https://github.com/nashsu/llm_wiki
Canonical: https://ross.abutalabs.com/products/llm_wiki
Language: TypeScript
License: NOASSERTION
License Family: other
Last push: 2026-08-25T06:42:02+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 99, longevity 10
- inputs: {"age_days": 147, "days_push": 8, "days_rel": 8, "gap_med": 1, "n_releases_24m": 60}
- flags: young, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 16834, forks 1993 (observed 2026-08-28T04:11:17.358584+00:00)

## What it is
LLM Wiki is a cross-platform desktop application that automatically turns your documents into an organized, interlinked knowledge base. Unlike traditional RAG, it incrementally builds and maintains a persistent wiki from your sources, with a knowledge graph, semantic search, and a tool-using chat agent backed by a Rust runtime.

## Use cases
- build a personal wiki from my pdfs and epub books automatically
- turn a folder of documents into an interlinked knowledge base
- chat with my documents with source-grounded answers
- extract images from pdfs and caption them with a vision llm
- discover clusters and connections in my notes with a knowledge graph
- run deep research on the web and ingest results into my wiki
- search my document library with vector semantic search

## When to choose
- you want a self-maintaining knowledge base rather than one-off RAG answers
- you need multi-format ingestion (PDF, Office, EPUB, web clips) with source traceability
- you want graph-based insights like community detection and knowledge gaps
- you prefer a local desktop app with configurable LLM providers

## When to avoid
- you need a lightweight library to embed into your own app
- you want a pure cloud-hosted collaborative wiki
- you require a permissive open-source license (license is non-standard)
- you only need simple full-text search without LLM processing

## Facets
- artifact type: application
- maturity: active
- function: rag, nlp, search-engine, llm-inference, chatbot, pdf, data-visualization
- domain: large-language-models, developer-tools
- platform: cross-platform, windows
- tags: knowledge-base, wiki-generator, document-ingestion, knowledge-graph, lancedb, vector-search, rust-backend, tauri, deep-research, personal-knowledge-management, retrieval-augmented-generation, knowledge-management, natural-language-processing, desktop, macos, linux

## Member repositories
- nashsu/llm_wiki (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:17.358584+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:03:49.101047+00:00, confidence not recorded.
  - readme: https://github.com/nashsu/llm_wiki (fetched 2026-08-28T04:11:17.358584+00:00, sha 33661a764d85)
- Data as of 2026-08-30T08:39:29.467469+00:00.