LLM Wiki v2 is another ready-to-use take on Karpathy’s LLM Wiki idea: drop in documents, and it files them into folders of Markdown notes, then answers questions with citations. It’s similar to SecondBrain, but a small classifier (hello, Jev) makes the filing decisions, so the big model isn’t called for every step.
- LLM Wiki v2 is an open-source tool that ingests documents and organizes them into a self-hosted Markdown wiki, answering questions with cited notes using any major AI provider or a local Ollama model.
- Its CROW mode uses a small typed classifier to handle routing and matching decisions, using 68% fewer LLM tokens than classic mode while being roughly twice as fast per ingest.
- The wiki stores everything as Markdown files on disk, compatible with git and any text editor, and exposes a Python library and HTTP API for developers to extend or automate.
