MCPgee
MCPgee
MCPgeeMCPgee

LLMWiki

v1.0.0•Knowledge & Memory•stable

Open Source Implementation of Karpathy's LLM Wiki. Upload documents, connect your Claude account via MCP, and have it write your wiki !

agentsai-agentsclaudekarpathyknowledge-base
Share:
950
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is LLMWiki?

LLMWiki is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to open source implementation of karpathy's llm wiki. upload documents, connect your claude account via mcp, and have it write your wiki !

Open Source Implementation of Karpathy's LLM Wiki. Upload documents, connect your Claude account via MCP, and have it write your wiki !

This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Open Source Implementation of Karpathy's LLM Wiki. Upload do

Use Cases

Wiki generation from document uploads
Knowledge base creation with Claude integration
lucasastorian

Maintainer

LicenseApache-2.0
Languagepython
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx llmwiki

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use LLMWiki

LLMWiki is an open-source implementation of Andrej Karpathy's LLM Wiki concept that lets you upload documents and have Claude automatically generate a structured wiki from them using an MCP integration. The system provides a local API and web UI for managing document workspaces, and exposes MCP tools so Claude can read, search, create, and edit wiki pages directly within a conversation. It is ideal for researchers and knowledge workers who want to turn collections of PDFs, notes, and source documents into a navigable, AI-authored knowledge base.

Prerequisites

  • Python 3.10+ with pip and venv
  • Node.js and npm for the web frontend
  • Claude Desktop or Claude Code with MCP support
  • Optional: Mistral API key (MISTRAL_API_KEY) for enhanced PDF OCR
  • Optional: PostgreSQL, Supabase account, and AWS S3 bucket for hosted/multi-user mode
1

Clone the repository

Clone LLMWiki and navigate into the project directory.

git clone https://github.com/lucasastorian/llmwiki.git
cd llmwiki
2

Install Python API dependencies

Create a virtual environment and install the backend dependencies.

cd api && python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt
cd ..
3

Install Node.js web frontend dependencies

Install the dependencies for the Next.js web interface.

cd web && npm install && cd ..
4

Initialize a workspace

Create a new LLMWiki workspace directory where your documents and generated wiki pages will be stored.

./llmwiki init ~/my-research-wiki
5

Start all services

Launch the API server and web UI in one command. The web interface will be available at http://localhost:3000.

./llmwiki serve ~/my-research-wiki
6

Generate your Claude Desktop MCP config

Run the mcp-config command to get the exact JSON snippet to add to your claude_desktop_config.json, then paste it in and restart Claude Desktop.

./llmwiki mcp-config ~/my-research-wiki

LLMWiki Examples

Client configuration for LLMWiki

MCP server configuration block for Claude Desktop after running llmwiki mcp-config.

{
  "mcpServers": {
    "llmwiki": {
      "command": "npx",
      "args": ["llmwiki"],
      "env": {
        "LLMWIKI_WORKSPACE": "/Users/you/my-research-wiki",
        "MISTRAL_API_KEY": "your-mistral-key-optional"
      }
    }
  }
}

Prompts to try

Example prompts for building and navigating your LLMWiki.

- "Read the guide, then ingest all documents in my workspace and start building the wiki"
- "Search the wiki for everything related to transformer architecture"
- "Create a new wiki page summarizing the key findings from the uploaded research papers"
- "What documents do I have in my workspace and what topics do they cover?"
- "Edit the 'Introduction' page to add a section on recent developments from the 2024 papers"

Troubleshooting LLMWiki

PDF files are not being parsed correctly or text extraction is poor

Set the MISTRAL_API_KEY environment variable to enable Mistral's enhanced OCR pipeline for PDF processing. This significantly improves accuracy for scanned documents.

MCP tools are not appearing in Claude Desktop after configuration

Run './llmwiki mcp-config ~/your-workspace' again to get the exact config snippet, ensure the workspace path is absolute, and fully restart Claude Desktop (not just reload).

The web UI is inaccessible or the API server fails to start

Ensure both the Python venv is activated and the workspace was initialized with 'llmwiki init' before running 'llmwiki serve'. Check that ports 3000 and 8000 are not in use by other processes.

Frequently Asked Questions about LLMWiki

What is LLMWiki?

LLMWiki is a Model Context Protocol (MCP) server that open source implementation of karpathy's llm wiki. upload documents, connect your claude account via mcp, and have it write your wiki ! It connects AI assistants to external tools and data sources through a standardized interface.

How do I install LLMWiki?

Follow the installation instructions on the LLMWiki GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with LLMWiki?

LLMWiki works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is LLMWiki free to use?

Yes, LLMWiki is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

LLMWiki Alternatives — Similar Knowledge & Memory Servers

Looking for alternatives to LLMWiki? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.

MemPalace

★ 52.6k

A local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically

Kratos

★ 25.7k

🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.

Context Mode

★ 15.4k

An MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm

Memu

★ 13.7k

Memory for 24/7 proactive agents like OpenClaw.

MemOS

★ 9.3k

MemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u

Everos

★ 5.4k

Build, evaluate, and integrate long-term memory for self-evolving agents.

Browse More Knowledge & Memory MCP Servers

Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Knowledge & MemoryBrowse All Servers

Quick Config Preview

{ "mcpServers": { "llmwiki": { "command": "npx", "args": ["-y", "llmwiki"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use LLMWiki?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides