Vane is a privacy-focused AI-powered answering engine that combines web search, AI reasoning, and multiple language model providers into a locally controlled search experience. The platform supports both local LLMs through Ollama and cloud providers such as OpenAI, Claude, Gemini, and Groq, giving users flexibility in how queries are processed. It integrates web search through SearxNG while also supporting discussions, academic sources, image search, and video search to generate citation-backed responses. Vane includes multiple search modes optimized for speed, balanced usage, or deep research depending on the complexity of the query. Its architecture emphasizes modular orchestration, custom provider systems, streaming responses, and widget-based UI enhancements for calculations, weather, and contextual data. Designed as a local-first alternative to commercial AI search engines, the project prioritizes privacy, extensibility, and transparent source-backed answers.

Features

  • Privacy-focused AI answering engine
  • Support for local and cloud-based LLMs
  • Citation-backed web and academic search
  • Multiple search quality and speed modes
  • Streaming responses with modular orchestration
  • Widgets for contextual quick-look information

Project Samples

Project Activity

See All Activity >

Categories

AI Agents

License

MIT License

Follow Vane

Vane Web Site

Other Useful Business Software
99.99% Uptime for MySQL and PostgreSQL Databases Icon
99.99% Uptime for MySQL and PostgreSQL Databases

Sub-second maintenance. 2x read/write performance. Built-in vector search for AI apps.

Cloud SQL Enterprise Plus delivers near-zero downtime with 35 days of point-in-time recovery. Supports MySQL, PostgreSQL, and SQL Server.
Start Free
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of Vane!

Additional Project Details

Operating Systems

Linux, Mac, Windows

Programming Language

TypeScript

Related Categories

TypeScript AI Agents

Registered

2026-05-06