ai-agent

llm_wiki: Auto‑build an interlinked knowledge base from your docs

Founders get a searchable, self‑updating wiki that organizes all project documents automatically—ideal for teams needing fast, persistent knowledge. 20k+ GitHub stars

From the repo · “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。”

intermediate⏱ 30 minutes💵 Free (self-hosted)
20,870 stars+207★ this week2,363 forksTypeScriptGuide quality 9/10 · reviewed Oct 5Updated 10/21/2026100% free · open source
What it is

Turns your documents into an organized, interlinked knowledge base automatically.

Real use case example

"A founder wants to create a centralized knowledge base for product documentation. They upload their internal documents, which are then automatically organized into a wiki. They can then link related documents and search through the knowledge base for answers, replacing the need for multiple spreadsheets or folders."

Best insideCursorClaude DesktopCodex CLIAny AI Client
When to use it
  • •You have a large collection of documents and want to create a searchable knowledge base without manual effort.
  • •Your team needs to share knowledge and collaborate on document-based projects.
  • •You want to build a personal knowledge management system to organize your notes and research.
Ready-to-paste prompt
Create a new knowledge base from afolder of documents: `npm run start -- --input=/path/to/documents --output=/path/to/knowledge/base`
Heads up: Make sure you have Node.js 16.14 or higher installed, as LLM Wiki requires this version to run.
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🖥️ Needs desktop apps

Drives software that must already be installed on your computer.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/llm-wiki && curl -fsSL https://workflowstacks.com/api/skills/llm-wiki/claude-skill -o ~/.claude/skills/llm-wiki/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How llm_wiki: Auto‑build an interlinked knowledge base from your docs works
Codeflow
Free to inspect

Llm_wiki: Auto‑build an interlinked knowledge base from your docs is a very large TypeScript project (~122k lines across 395 code files, plus 7 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Other license, has a test suite.

Size
Very large codebase
~122k lines · 395 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Node.js
No API keys detected
TypeScript 71%Rust 26%JavaScript 3%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    src/App.tsx
    Where the program starts running
  3. 3
    package.json
    Dependencies and the commands it exposes
What's in each folder
src/Core code — the actual logic353 files
extension/Sub-packages / plugins10 files
src-tauri/Folder60 files
mcp-server/Folder10 files
plans/Folder1 files
scripts/Helper scripts1 files
assets/Images & static assets9 files
.github/CI / automation (GitHub Actions)3 files
READMEHas testsDocumentedCI checksOther licenseUpdated this month
Quick Actions
Details
Creator
nashsu
Language
TypeScript
Category
ai-agent
Published
4/8/2026

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/llm-wiki.svg)](https://workflowstacks.com/skills/llm-wiki?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.