Vane (formerly Perplexica) is a self-hosted AI search engine for people who want answers drawn from web results, with citations they can check. It runs on your own hardware through Docker or as a server application, with a browser interface and locally stored search history. The project is free and open source under the MIT license.
Web search uses SearxNG, either bundled with Vane or running as a separate instance. Searching the web requires an internet connection. For answers, Vane can use a local LLM through Ollama or an OpenAI-compatible server, including Lemonade. It also supports hosted models from OpenAI, Anthropic Claude, Google Gemini, and Groq; requests to those providers leave your machine.
Search can focus on web pages, discussions, or academic papers, and domain filters help when you want results from a particular site. Speed, Balanced, and Quality modes offer different levels of research depth. Image and video results are available alongside text results, and relevant searches can display weather, calculations, or stock information.
Vane also lets you upload PDFs, text files, and images to ask questions about their contents. Search suggestions help shape queries, while Discover offers articles and trending content to browse. An API makes its search and answers available to other applications, and Vane can be added to a browser's search bar.
Claim this page and we'll verify you by hand. Vane (formerly Perplexica) gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find Vane (formerly Perplexica)?Promote it
Something wrong or outdated on this page?
18.3KUpdated 24 hours agoMIT
macOS · Windows · Linux · Docker · Web#Human approval#Hybrid search#llama.cpp backend
DocsGPT is an MIT-licensed, open-source platform for teams that want AI search, assistants and agents over their own documents. It can run on your servers with local models, including fully air-gapped deployments where documents and questions stay inside your network. Answers include the source title and page number so readers can check the evidence.
9.1KUpdated 21 hours agoMIT
macOS · Windows · Linux · Docker · Web#llama.cpp backend#MCP#Multi-user access
Local Deep Research is a self-hosted AI research assistant for people who need cited answers drawn from academic papers, the web and their own documents. It can produce a quick summary or pursue a complex question through repeated searches, then assemble a structured report. It's open source under MIT.
32.3KUpdated 24 hours ago
Docker · Web · Browser Extension#MCP#Multi-user access#Ollama integration
Onyx is an AI search and chat platform for teams whose information is spread across workplace apps. It indexes company knowledge so employees can ask questions across sources and get answers grounded in relevant documents. Teams can deploy it in their own cloud or on bare metal, including an air-gapped environment.
11.9KUpdated 2 months agoAGPL-3.0
Web#Code execution#Multilingual#RAG
Scira is an AI search engine for people who want answers backed by sources and control over the application they use for research. It has a hosted website, and you can self-host the open-source application under AGPL-3.0. Its live search relies on internet access and external services; self-hosting doesn't make that research offline.
37.5KUpdated 2 months agoAGPL-3.0
Web#RAG#Semantic search#Web search
Khoj is an AI assistant for people who want to ask questions across their own files, research the web, and give recurring work to agents. You can self-host it on your computer or server, or use Khoj's cloud app. It's open source under the GNU AGPL v3.0 license.
77KUpdated 3 months agoAGPL-3.0
macOS · Windows · Linux · iOS · Android · Web#MCP#Multi-user access#RAG
AppFlowy is a self-hosted Notion alternative for teams that want project management, shared documents, and AI in an environment they control. Its self-hosted enterprise offering can run on premises, in your own cloud, or in an air-gapped environment. Self-hosted LLMs and embedding models let you keep AI processing and workspace data inside your infrastructure, with no vendor access to your instance.