Vane

Overview

Vane is a privacy-focused AI answering engine that runs entirely on your own hardware. It combines knowledge from the internet with support for local LLMs (Ollama) and cloud providers (OpenAI, Claude, Groq), delivering accurate answers with cited sources while keeping searches private.

Key Features

• Support for major AI providers (Ollama, OpenAI, Claude, Gemini, Groq)
• Smart search modes: Speed, Balanced, Quality
• Source selection: web, discussions, academic papers
• Widgets for weather, calculations, stock prices
• Web search powered by SearxNG with privacy
• File uploads for PDFs, text, images

Use Cases

• Private personal search with cited answers
• Deep research using academic sources
• Alternative to traditional search engines
• Integration via API for developers

Getting Started

• Run with Docker: docker run -d -p 3000:3000 -v vane-data:/home/vane/data --name vane itzcrazykns1337/vane:latest. For non-Docker: clone repo, npm i, npm run build, npm run start. Access at http://localhost:3000 and configure settings.

Deployment & Requirements

• Docker recommended; image includes SearxNG. For external SearxNG, set SEARXNG_API_URL and ensure JSON and Wolfram Alpha enabled. API keys for AI providers required. Persistent volume for data. Port 3000 exposed.

Before You Adopt

• License: MIT. Review its terms before using, modifying, or distributing the project.