Vane
Privacy-first AI answer engine running fully on your hardware. Combines web search with local LLMs (Ollama) and cloud providers (OpenAI, Claude, Groq). All data stays local.
Smart Download
Visit Project Homepage
No installer available yet — head to the source repository
Run your own private AI search engine with local or cloud models, answers include citations.
Core Features
- Supports Ollama (local) and cloud models (OpenAI, Claude, Gemini, Groq) – mix and match
- Three search modes: Speed, Balanced, Quality for different needs
- Choose sources: web, discussions, academic papers; more coming soon
- Widgets: weather, calculations, stock prices, etc.
- Image & video search, file uploads (PDF, images)
What It Can't Do
- •For Ollama in Docker, set API URL to http://host.docker.internal:11434 (Windows) or host IP. Ensure local LLM server listens on 0.0.0.0, not 127.0.0.1. Non-Docker setup requires separate SearxNG with JSON format enabled.
Use Cases
- Privacy-conscious users who want to avoid cloud data collection
- Developers running local LLMs (Ollama) needing web-enhanced answers
- Academic research with domain-limited searches and cited sources
Vane is a self-hosted AI answer engine that prioritizes your privacy. It integrates with SearxNG for private web search and supports multiple AI providers: local models via Ollama, or cloud APIs like OpenAI, Claude, Gemini, Groq. You can mix models and search modes (Speed, Balanced, Quality) for different needs. Features include widgets (weather, calculations), image/video search, file uploads (PDF, images), domain-specific search, search history, and smart suggestions. All data stays on your machine. Docker installation is recommended for easy setup with bundled SearxNG.
Tags
Getting Started
Download installer
Click the button above to download the installer for your system
Install the software
Double-click the downloaded installer and follow the prompts
Step 1: Install Docker, then run: docker run -d -p 3000:3000 -v vane-data:/home/vane/data --name vane itzcrazykns1337/vane:latest
Step 2: Open http://localhost:3000, configure AI providers and search (SearxNG is bundled)
Step 3: Start searching – choose speed/balanced/quality mode, upload files, or restrict to specific domains
- Step 1: Install Docker, then run: docker run -d -p 3000:3000 -v vane-data:/home/vane/data --name vane itzcrazykns1337/vane:latest
- Step 2: Open http://localhost:3000, configure AI providers and search (SearxNG is bundled)
- Step 3: Start searching – choose speed/balanced/quality mode, upload files, or restrict to specific domains
Checksum not available
This project has not published a SHA-256 checksum on its GitHub Release page
SHA256 Checksum
No checksum available
Download directly from GitHub Releases and verify file integrity yourself
All SHA-256 checksums on this platform are extracted from the project's official GitHub Release page, without any modification. You can independently verify them on the GitHub Releases page.
Open Source Transparency
View GitHub SourceUninstall Info
Stop and remove container: docker stop vane && docker rm vane. To delete persistent data: docker volume rm vane-data.
No Extra Dependencies
Ready to use after download. No additional runtime required.
Having issues? Check the FAQ below
3 FAQs
Similar Projects
Chatbox
Chatbox Community Edition is an open-source desktop client for interacting with multiple large language models. It supports OpenAI (ChatGPT), Azure OpenAI, Claude, Google Gemini Pro, Ollama (local models like Llama 2, Mistral), and ChatGLM-6B. All your chat data is stored locally on your device, ensuring privacy and preventing data loss. The app features a clean, ergonomic UI with dark mode, keyboard shortcuts, streaming replies, and full Markdown/LaTeX rendering with code highlighting. It also includes a prompt library, message quoting, and team collaboration for sharing API resources. Available on Windows, macOS, Linux, Web, iOS, and Android. The community edition is fully functional but may lack some advanced features from the pro version.
ollama
Ollama lets you download, run, and manage large language models locally. One command, multiple platforms, endless possibilities.
llama.cpp
High-performance LLM inference engine in C/C++ with minimal dependencies, supporting quantized models (1.5–8 bit) and diverse hardware (Apple Silicon, CUDA, Vulkan, etc.).