---
title: "Deploy Vane (Perplexica)"
description: "Self-hosted AI answer engine (formerly Perplexica) with login and storage"
category: "AI/ML"
url: https://railway.com/deploy/vane-perplexica
---

# Deploy Vane (Perplexica)

Self-hosted AI answer engine (formerly Perplexica) with login and storage

**[Deploy Vane (Perplexica) on Railway](https://railway.com/template/vane-perplexica)**

Machine-readable deploy manifest (JSON, validated by TemplateCI): https://railway.com/deploy/vane-perplexica/manifest.json

- **Creator:** Agaz Self-Host
- **Category:** AI/ML

## Template content

### Vane https://raw.githubusercontent.com/ItzCrazyKns/Vane/v1.12.2/public/icon.png

- **Source:** https://github.com/aalfath/vane-railway-template
- **Health check:** /healthz
- **Public domain:** Yes

## Documentation

# Deploy and Host Vane (Perplexica) on Railway

Vane, called Perplexica until 2026, is an open-source AI answering engine you host yourself. It searches the web through a bundled SearXNG instance, reads the top pages and writes an answer with cited sources. It works with OpenAI, Anthropic, Gemini, Groq, Ollama, LM Studio or any OpenAI-compatible API, and keeps your chat history.

## About Hosting Vane (Perplexica)

This template runs the official Vane v1.12.2 image, pinned by version and digest, as one service. The image includes SearXNG and a headless Chromium for reading pages. Vane has no accounts, and its settings API returns the provider API keys you save. So a small Caddy proxy in front adds a login (user `admin`, password generated per deploy, shown in the service's Variables tab). SearXNG and Vane listen only inside the container. Settings, provider keys, chat history (SQLite) and uploaded files live on a Railway volume, so they survive redeploys and updates. After the first deploy, log in and add an LLM provider in the setup screen.

## Common Use Cases

* A private, self-hosted alternative to Perplexity for web research with cited sources
* Asking questions about uploaded PDFs, documents and images
* Searching academic papers, discussions or specific sites with your own LLM keys or local models

## Dependencies for Vane (Perplexica) Hosting

* An API key for at least one LLM provider (OpenAI, Anthropic, Gemini, Groq and others), or a reachable Ollama, LM Studio or OpenAI-compatible server
* A Railway volume for settings and chat history (included)

### Deployment Dependencies

* Vane source and releases: https://github.com/ItzCrazyKns/Vane (v1.12.2)
* Official image: https://hub.docker.com/r/itzcrazykns1337/vane
* Template repository: https://github.com/aalfath/vane-railway-template

### Implementation Details

* Log in with `VANE_USERNAME` (default `admin`) and `VANE_PASSWORD` (generated). To change the password, edit `VANE_PASSWORD` (at least 12 characters) and redeploy.
* Provider keys are added in Vane's setup screen. You can also set `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, `GEMINI_API_KEY`, `GROQ_API_KEY` or `OLLAMA_BASE_URL` as service variables.
* Updates: the service builds from the template repository. When a new Vane version is pinned there, Railway shows an update notice on your project. Read `CHANGELOG.md` in the repository before applying it. Your volume is kept.
* The health check is `/healthz`, which needs no login.

## Why Deploy Vane (Perplexica) on Railway?


Railway is a singular platform to deploy your infrastructure stack. Railway will host your infrastructure so you don't have to deal with configuration, while allowing you to vertically and horizontally scale it.

By deploying Vane (Perplexica) on Railway, you are one step closer to supporting a complete full-stack application with minimal burden. Host your servers, databases, AI agents, and more on Railway.



## Similar templates

- [Chat Chat](https://railway.com/deploy/-WWW5r) — Chat Chat, your own unified chat and search to AI platform.
- [Weaviate](https://railway.com/deploy/weaviate-1) — Vector database with hybrid search and an API key-protected API
- [Möbius Personal AI OS](https://railway.com/deploy/mobius-v01-personal-ai-os) — Self-hosted AI agent that builds and runs apps for you, with memory.

Open this page in a browser: https://railway.com/deploy/vane-perplexica
