#105 · Primary category: Knowledge Base & RAG
llmwiki
Open Source Implementation of Karpathy's LLM Wiki. Upload documents, connect your Claude account via MCP, and have it write your wiki !
Project last updated:08/09/26
GitHub Stars
1.5K
Forks
226
Contributors
5
License
Apache-2.0
Why we included this project
LLM Wiki is built on the idea that your reading notes should keep working for you long after you close the tab. Point it at a folder of documents, connect Claude through MCP, and a scheduled agent turns new material into wiki-style pages that cross-link back to the sources they came from. The part that stands out is the autonomous loop: a Chrome extension clips pages and PDFs as you read, keeps your highlights and margin notes, and Claude folds them into the knowledge base on its own, so it gets more useful over months instead of going stale. A Next.js web app and a graph view make browsing practical, and since you can self-host it, researchers or small teams can treat it as a personal or institutional memory that an LLM maintains for them. The design follows Andrej Karpathy's LLM Wiki concept.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
ragflow
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
Understand-Anything
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
crawl4ai
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
docling
Get your documents ready for gen AI
anything-llm
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience