#87 · Primary category: Knowledge Base & RAG
llm-wiki-compiler
The knowledge compiler. Raw sources in, interlinked wiki out. Inspired by Karpathy's LLM Wiki pattern.
Project last updated:08/27/26
GitHub Stars
2.0K
Forks
197
Contributors
13
License
MIT
Why we included this project
llmwiki is for anyone who keeps handing an LLM the same stack of papers and notes and would rather those sources build on each other than get re-read from scratch every time. It compiles raw material into interlinked markdown pages that carry citations and freshness checks, so a team ends up with a durable knowledge base that agents and humans can browse or query instead of loose files. Because every page traces back to its sources, generated knowledge stays auditable as it accumulates over weeks of updates. Optional lifecycle profiles let you model entities and workflows for a specific field, and the output works from the CLI, over MCP, or through the SDK, so it slots into an existing agent setup. It is not a general static-site generator; it earns its keep when the source knowledge is worth compiling and reusing rather than searched fresh every time.
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