#99 · Primary category: Knowledge Base & RAG
karpathy-llm-wiki
Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting.
Project last updated:07/23/26
GitHub Stars
2.1K
Forks
248
Contributors
1
License
MIT
Why we included this project
Instead of re-searching raw documents every time you ask something, this skill has the coding agent compile new sources into durable markdown pages and refresh them as the material grows. It wraps Karpathy's LLM wiki concept into an installable Agent Skills component for Claude Code, Cursor, and Codex. The workflow covers three operations: ingest sources into a raw folder for triage, query the wiki for answers with citations, and lint for broken links and index integrity. That makes it a sensible choice when you want a curated, cross-linked knowledge base in version-controlled markdown rather than a full RAG pipeline, and answers stay grounded because they cite the wiki pages that synthesized the material.
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