vane

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) and cloud providers (OpenAI, Claude, Groq), delivering accurate answers with cited sources while keeping your searches completely private. ## Features - **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 needs. - **Smart search modes**: Choose Speed Mode for quick answers, Balanced Mode for everyday searches, or Quality Mode for deep research. - **Pick your sources**: Search the web, discussions, or academic papers. More sources and integrations are in progress. - **Widgets**: Helpful UI cards that show up when relevant, like weather, calculations, stock prices, and other quick lookups. - **Web search powered by SearxNG**: Access multiple search engines while keeping your identity private. Support for Tavily and Exa coming soon. - **Image and video search**: Find visual content alongside text results. - **File uploads**: Upload documents and ask questions about them. PDFs, text files, images - Vane understands them all. - **Search specific domains**: Limit your search to specific websites when you know where to look. - **Smart suggestions**: Get intelligent search suggestions as you type. - **Discover**: Browse interesting articles and trending content throughout the day. - **Search history**: Every search is saved locally so you can revisit your discoveries anytime. ## Installation ### Docker (Recommended) ```bash docker run -d -p 3000:3000 -v vane-data:/home/vane/data --name vane itzcrazykns1337/vane:latest ``` This pulls and starts the Vane container with the bundled SearxNG search engine. Access at http://localhost:3000. ### Using with Your Own SearxNG Instance ```bash docker run -d -p 3000:3000 -e SEARXNG_API_URL=http://your-searxng-url:8080 -v vane-data:/home/vane/data --name vane itzcrazykns1337/vane:slim-latest ``` Ensure your SearxNG instance has JSON format enabled and Wolfram Alpha search engine enabled. ### Non-Docker Installation 1. Install SearXNG and allow JSON format. 2. Clone the repository and run `npm i`. 3. Build with `npm run build` and start with `npm run start`. 4. Access at http://localhost:3000. ## Troubleshooting - **Local OpenAI-API-Compliant Servers**: Ensure server runs on `0.0.0.0`, correct model name, and API key. - **Ollama Connection Errors**: Check API URL. Use `http://host.docker.internal:11434` on Windows/Mac, `http://<private_ip>:11434` on Linux. Expose Ollama to network with `OLLAMA_HOST=0.0.0.0:11434`. - **Lemonade Connection Errors**: Similar steps with port 8000. ## Using as a Search Engine Add a site search with URL `http://localhost:3000/?q=%s` in browser settings. ## API Vane provides an API for developers to integrate its search engine. See docs for details. ## One-Click Deployment Deploy to Sealos, RepoCloud, ClawCloud, or Hostinger with provided buttons. ## Upcoming Features - More widgets, integrations, search sources - Custom agents - Authentication ## Support Star the repo, donate via Ethereum, or contribute via GitHub Issues. Join Discord for community support.