A self-hosted AI answering engine that runs on your own hardware to keep searches private. It combines local or cloud LLMs with web search to deliver cited answers.
Project overview
A self-hosted AI answering engine that runs on your own hardware to keep searches private. It combines local or cloud LLMs with web search to deliver cited answers.
Project type
RAG · AI Search
Use cases
Chat Assistants · Search & Research
Deployment
Refer to project documentation
License
MIT
Best for
General users and developers who want a self-hosted AI answering engine that keeps search history local and uses their own hardware.
Key capabilities
Use local LLMs through Ollama or connect to OpenAI, Anthropic Claude, Google Gemini, Groq, and more.
Choose Speed Mode for quick answers, Balanced Mode for everyday searches, or Quality Mode for deep research.
Access multiple search engines while keeping your identity private.
Find visual content alongside text results.
Upload documents and ask questions about them. PDFs, text files, images are supported.
Limit your search to specific websites when you know where to look.
Every search is saved locally so you can revisit your discoveries anytime.
Helpful UI cards that show up when relevant, like weather, calculations, stock prices, and other quick lookups.
Limitations and risks
Requires external SearxNG setup with JSON and Wolfram Alpha enabled if using a non-Docker installation or the slim image.
Getting started
Docker is recommended to simplify setup by bundling dependencies. You can start by running the container, opening a browser to localhost:3000, and configuring settings on the setup screen.
Evidence and sources
README: Vane is a **privacy-focused AI answering engine** that runs entirely on your own hardware. It combines knowledge from the vast internet with support for **local LLMs** (Ollama) an…
README: 🤖 Support for all major AI providers - Use local LLMs through Ollama or connect to OpenAI, Anthropic Claude, Google Gemini, Groq, and more. Mix and match models based on your need…
README: docker run -d -p 3000:3000 -v vane-data:/home/vane/data --name vane itzcrazykns1337/vane:latest This will pull and start the Vane container with the bundled SearxNG search engine.…
README: If you already have SearxNG running, you can use the slim version of Vane: ```bash docker run -d -p 3000:3000 -e SEARXNG_API_URL=http://your-searxng-url:8080 -v vane-data:/home/va…
README: If you prefer to build from source or need more control: 1. Ensure Docker is installed and running on your system. 2. Clone the Vane repository: ```bash git clone https://github.c…