LLM Wiki: Turn Your Documents Into an Interlinked Knowledge

TL;DR

TL;DR: LLM Wiki is a cross-platform desktop app that ingests a folder of documents and turns it into an organized, interlinked knowledge base. The “LLM” in the name is descriptive — the app uses an LLM to extract entities, link documents, and answer questions against the corpus. Everything runs locally on the desktop.

What Is LLM Wiki?

The repository description: “LLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base.” That is the whole product summary. It is a desktop app, it reads documents, and it builds a knowledge graph you can navigate and query.

The interesting design choice is the “interlinked” part. Most document Q&A tools stop at retrieval — ask a question, get a chunk of text back. LLM Wiki goes further: it extracts entities, builds links between documents, and exposes a navigable structure alongside the natural language interface.

How It Works

The TypeScript codebase targets Electron or a similar cross-platform desktop shell. The implied pipeline is:

• Ingest any folder of supported documents — PDFs, markdown, plain text, etc.
• Run an LLM pass to extract entities, summaries, and relationships.
• Persist the resulting graph locally so it survives across sessions.
• Expose a query interface that lets the user ask questions against the corpus, with the graph as the retrieval backbone.

Because the app is desktop-local, your documents never leave the machine for indexing. The LLM calls themselves may hit a hosted provider, but the corpus stays in your filesystem.

Repo Facts

• Repository: nashsu/llm_wiki
• Language: TypeScript
• License: NOASSERTION (verify the LICENSE file before redistribution)
• Stars at time of writing: 18,758

When To Use It

LLM Wiki is the right tool when:

• You have a folder of notes, PDFs, or research that you want to query and navigate.
• You want a local-first knowledge base, not a hosted service that holds your data.
• You are comfortable providing an LLM API key for the extraction step.

It is not a collaborative wiki, it is not a Notion replacement, and it is not a vector store you point your own agents at. It is a desktop app that owns one user’s corpus and the graph view over it.

Source and Accuracy Notes

• Project page: https://github.com/nashsu/llm_wiki
• Source repository: nashsu/llm_wiki (verified via GitHub API html_url)
• License: NOASSERTION (read the LICENSE file in the repo before redistribution)
• Stars at time of writing: 18,758
• The repository does not list GitHub topics; all feature claims are grounded in the repository description. Check the README for the exact list of supported document types and LLM providers.