Back to directory

Vane

A self-hosted AI answering engine that searches the web and cites its sources, combining local models through Ollama or cloud providers with a bundled private web search backend.

Vane

Vane answers a question by searching the web through a bundled SearxNG instance, which queries multiple search engines while keeping the user's identity private, and then generates a cited answer using a chosen local or cloud language model, including OpenAI, Anthropic Claude, Google Gemini and Groq. It offers speed, balanced and quality search modes, can search the web, discussions or academic papers, and can also search images and video alongside text.

Users can upload documents, including PDFs, text files and images, and ask questions about them, restrict a search to specific domains, and browse a discover feed of trending content. Search history is saved locally so past searches can be revisited.

It runs as a Docker container bundling both Vane and SearxNG, or against an existing SearxNG instance using a slim image. It is written in TypeScript and licensed under the MIT license.

More in RAG

See all 540
  • ai·rete·rag

    ai-rete-rag.com

    A platform that pairs a Rete rule engine with retrieval-augmented generation, so deterministic rules decide an outcome and grounded retrieval explains the decision in plain language.

  • Xtriever

    github.com

    A hybrid retrieval engine for retrieval-augmented generation, written in Rust to run on-device on a phone or a laptop, combining lexical BM25 search, dense embedding search, reciprocal-rank fusion and cross-encoder re-ranking with no server.

  • FileFlux

    github.com

    A .NET library that turns PDF, DOCX, HWP and other documents into optimized chunks for RAG systems, through a five-stage pipeline built on high-performance Rust FFI readers.