# lilbee plugin for Obsidian lilbee, by tobocop2, runs a local AI search engine against your vault, inside Obsidian. Ask a question in plain English, and it answers from your notes, with citations that click straight back to the source line. That's local RAG (retrieval-augmented generation): the model answers from passages it first retrieved from your notes. It also comes with a web crawler that saves sites to your vault, an auto-generated wiki, and a model catalog. The plugin downloads and manages the lilbee server and the models itself. You don't need [[Ollama]], but lilbee uses Ollama, [[LM Studio]] or cloud models if you have them; cloud models are opt-in, per role. Heads up: the first launch downloads the server (a few hundred MB), and each model you pick adds more. It's desktop only, and Obsidian staff haven't reviewed it manually yet. Like [[Khoj plugin for Obsidian|Khoj]], it's a full local RAG stack: more setup and more moving parts than a related-notes panel. ## References - Source code: https://github.com/tobocop2/obsidian-lilbee - Community plugin page: https://obsidian.md/plugins?id=lilbee ## Related - [[The Complete Guide to Obsidian Search - Find Any Note When You Need It (Article)]] - [[Set Up AI Search for Your Obsidian Vault - qmd, MCP Servers and AI Assistants (Article)]] - [[Khoj plugin for Obsidian]] - [[Running AI Models Locally]] - [[Ollama]] - [[LM Studio]] - [[Obsidian AI Plugins]]