Understand the trade-offs
Decide whether running your own answer engine fits your workflow.
Compare the options ↗An independent guide to Vane
Your search.
Your rules.
Your infrastructure.
A practical starting point for self-hosted AI search. Explore Vane, build your Docker configuration, and bring your own model.
Open-source software. Your hosting. A little guidance from us.
YOUR SERVER / COMPOSE
# A small file. A search engine of your own.
services:
vane:
image: itzcrazykns1337/vane:latest
ports:
- "127.0.0.1:3000:3000"
volumes:
- vane-data:/home/vane/data↳ Start with Docker. Configure in your browser.
A clear path from question to source
Your question → Vane + search → Your model
Architecture illustration · not a live search
↗ OPEN SOURCE · MIT LICENSE◇ DOCKER CONFIGURATION⌘ LOCAL OR CLOUD MODELS
From curious to self-hosted
A shorter path to your first instance.
Start small. Understand what you run. Add public access when you’re ready.
Make it your deployment
Generate a Compose file with persistent data and a local-only port.
Build your configuration ↗Keep it running
Plan access, model spend, backups, and upgrades before sharing a server.
Read the launch checklist ↗Before you spin up a server.
Explore Vane →Is VaneDeploy the official Vane website?
No. This is an independent deployment guide and configuration tool. Vane is maintained by its upstream contributors.
Is self-hosting free?
The software has an MIT license. Your server, storage, backups, and model inference may cost money. Cloud model usage is billed by your provider.
Do all searches stay on my server?
No. Web search reaches external search services. If you select a cloud model, requests also leave your server. Review each provider’s data policy.
Can I run a local model on a small VPS?
It depends on the model and available memory. Start with a cloud provider for a small server, or benchmark a separate Ollama host before buying hardware.