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。

What it solves

LLM Wiki transforms fragmented documents into a structured, interlinked personal knowledge base automatically. Unlike traditional RAG systems that retrieve information on the fly, it incrementally builds and maintains a persistent wiki, ensuring knowledge is compiled once and kept current rather than re-derived for every query.

How it works

The system follows a three-layer architecture: Raw Sources (immutable) $\rightarrow$ Wiki (LLM-generated) $\rightarrow$ Schema (rules and configuration). It uses a two-step Chain-of-Thought ingest process where an LLM first analyzes sources for entities and connections, then generates the actual wiki pages with source traceability.

Key technical components include:

  • Knowledge Graph: A relevance model using direct links, source overlap, and community detection (Louvain algorithm) to visualize and discover knowledge clusters.
  • Retrieval Pipeline: A multi-phase process combining tokenized search, optional vector semantic search (via LanceDB), and graph expansion to provide context to the LLM.
  • Agentic Backend: A Rust-based chat agent capable of using tools for wiki/web search, file generation, and executing approved shell commands.
  • Deep Research: An automated pipeline that identifies knowledge gaps and uses web search (Tavily, SerpApi, SearXNG) to synthesize new information into the wiki.

Who it’s for

It is designed for researchers, students, and professionals who manage large volumes of documents and want an automated way to organize their notes, discover surprising connections between ideas, and maintain a long-term, structured knowledge base.

Highlights

  • Two-Step Ingest: Separates analysis from generation to improve wiki quality and source traceability.
  • Knowledge Graph Insights: Automatically detects "surprising connections," isolated pages, and knowledge gaps.
  • Deep Research: LLM-optimized web search that automatically ingests findings back into the wiki.
  • Obsidian Compatibility: The generated wiki directory functions as an Obsidian vault.
  • Multimodal Support: Extracts images from PDFs and generates factual captions using vision LLMs.
  • Agent Skills: Supports local SKILL.md files to extend the agent's capabilities.

Related

  • Project
    xoai/sage-wiki

    A graph-based knowledge base that compiles raw documents into an interlinked wiki, enabling AI agents and humans to query a structured knowledge graph with citations.

  • Project
    zosmaai/pi-llm-wiki

    pi‑llm‑wiki is an npm‑distributed, pi/oh‑my‑pi extension that builds a portable, Obsidian‑compatible markdown wiki from raw sources. It captures URLs, PDFs, etc., creates immutable source packets, ingests them into concept/entity/synthesis/analysis pages, and lets LLMs query the growing knowledge base with citations. The vault is layered (personal ~/.llm‑wiki, project /.llm‑wiki) and follows the Open Knowledge Format v0.2. A built‑in MCP server makes the wiki usable from Claude Code, Cursor, Windsurf, Zed, and other clients. Features include auto‑bootstrap, full‑text search, linting, dashboards, optional trajectory capture, and CI‑backed test coverage.

  • Project
    atomicstrata/llm-wiki-compiler

    llm‑wiki‑compiler is a Node/TS tool that compiles raw documents into a citation‑aware, typed markdown wiki, with review gates, lifecycle profiles, an SDK, and an MCP server for LLM agents.

  • Project
    shannhk/llm-wikid

    An AI-maintained knowledge base for Obsidian that compiles raw sources into a structured wiki, avoiding RAG by pre-building cross-references and compounding knowledge over time.

  • Project
    SamurAIGPT/llm-wiki-agent

    LLM Wiki Agent is a local, agent‑driven system that ingests PDFs, DOCX, markdown, etc., extracts entities and concepts, builds an ever‑growing inter‑linked markdown wiki, flags contradictions, and generates a visual knowledge graph—all without a server or database.