Open WebUI on Railway

A self-hosted chat interface for language models, with Ollama, search and RAG, on Railway.

Official site · License: Open WebUI License (BSD-3-Clause based, with branding clause) · 21 Railway templates

Deploy Open WebUI on RailwayCompare templates

Open WebUI is a self-hosted chat interface for language models. It connects to Ollama for local models or to any OpenAI-compatible API, and adds multi-user accounts, document chat with retrieval, web search and tools.

Individuals and teams use it as a private ChatGPT-style front end, so conversations and uploaded documents stay on a server they control while still allowing hosted models through an API key.

Open WebUI uses its own licence based on BSD-3-Clause with an added branding clause: the name and logo must stay visible unless you have 50 or fewer end users in a 30-day period, written permission, or an enterprise licence.

What Open WebUI can do

  • Chat interface for Ollama and OpenAI-compatible APIs
  • Multi-user accounts with admin approval
  • Document chat with retrieval (RAG)
  • Web search integration
  • Tools and model management in the UI

What people use it for

  • A private chat front end for a team
  • Running small local models with Ollama
  • Chatting with your own documents
  • Adding a shared UI in front of an OpenAI-compatible API

Videos

Self-Host a local AI platform! Ollama + Open WebUI · Christian Lempa
Beginners Guide to Installing Open WebUI · Professor Patterns
Is Open Webui The Ultimate Ollama Frontend Choice? · Matt Williams

Running Open WebUI on Railway

The Railway template deploys Open WebUI v0.12.0 with Ollama (pulling llama3.2:3b and nomic-embed-text on first boot), SearXNG for web search, Postgres with pgvector for users, chats and vectors, and Redis, with volumes for data. Railway has no GPUs, so models run on CPU and should stay small; memory and storage from Ollama and the models are the main cost drivers.

Open WebUI templates on Railway

Open WebUI + Ollama Private AIMaintained by Tracklayer
Open WebUI is a self-hosted chat interface for language models. This template deploys Open WebUI v0.12.0 with Ollama for local models, SearXNG for private web search, Postgres with
4 deployments
Deploy
Open WebUI by alphasec
User-friendly ChatGPT UI alternative designed to operate offline.
1,098 deployments
Deploy
Open WebUI with Pipelines by Tom
Open WebUI + Pipelines is an extendable, user friendly self-hosted LLM UI.
533 deployments
Deploy
Ollama + OpenWebUI by an independent creator
[Jun '26] Deploy open-source LLMs with a simple, private web interface.
232 deployments
Deploy
Open WebUI on Railway by Heimdall
[Jun '26] OpenWebUI | Self-hosted AI interface. Connect with any LLM model.
211 deployments
Deploy
Open WebUI [with Postgres & Redis] by an independent creator
Self-host OpenWebUI; Postgres survives redeploys, Redis scales sessions
167 deployments
Deploy
OpenWebUI [Updated Nov ’26] by an independent creator
OpenWebUI [Nov ’26] (Chat with Local or Remote AI Models) Self Host
88 deployments
Deploy
Open WebUI by an independent creator
OpenWebUI Pro Stack: Open Web UI, LiteLLM, persistent Postgres and Redis.
62 deployments
Deploy
Open WebUI with MCP by an independent creator
Open WebUI with MCP-to-OpenAPI proxy server
62 deployments
Deploy
Open WebUI by an independent creator
Private multi-model AI chat [Nov'26] — OpenAI, Claude, Ollama, built-in RAG
58 deployments
Deploy
Open WebUI by an independent creator
Run AI on your terms. Connect any model, extend code, protect data
17 deployments
Deploy
Open WebUI by an independent creator
Your self-hosted interface for local and cloud AI models.
11 deployments
Deploy
Open WebUI by an independent creator
Self-hosted AI chat for OpenAI-compatible APIs and local models.
10 deployments
Deploy
OpenWebUI by an independent creator
Self-host Open WebUI [Nov'26]— durable Postgres, scalable sessions
10 deployments
Deploy
llama.cpp + Open WebUI by an independent creator
Deploys llama.cpp (free tokens) +Open WebUI
8 deployments
Deploy
Ollama + Open WebUI | Fast CPU Inference, Model Preloaded by an independent creator
Ollama tuned for Railway CPU: 78x faster, model pulled on first boot.
7 deployments
Deploy
Open WebUI (All-in-One Bundle) by an independent creator
Open WebUI + PostgreSQL (pgvector) + Redis + SearXNG
5 deployments
Deploy
Open WebUI + Bifrost | Self-Hosted ChatGPT for Every LLM by an independent creator
Deploy and Host Open WebUI + Bifrost
5 deployments
Deploy
Open WebUI | Self-Hosted LLM Chat with a Real Volume by an independent creator
Self-hosted chat UI for LLMs, on a pinned release with a persistent volume
5 deployments
Deploy
DeepSeek Chat — Ollama + Open WebUI, Private AI by an independent creator
Run distilled DeepSeek models privately — Ollama + chat UI
4 deployments
Deploy
Open WebUI by an independent creator
Open WebUI on Postgres with pgvector, admin account set at deploy time
4 deployments
Deploy

Tracklayer templates are listed first. Other Open WebUI templates follow, ordered by total deployments on Railway. How this works.

Deployment numbers as of 2026-11-20.

Questions about Open WebUI

How do I log in?

Enter your email in WEBUI_ADMIN_EMAIL at deploy, then copy WEBUI_ADMIN_PASSWORD from the Open WebUI service variables and sign in at the public URL. New sign-ups stay pending until approved.

Why is the first start slow?

Ollama downloads about 2.3 GB of models on first boot. Wait for its logs to show both models pulled before starting a chat.

Can it run large models?

Not well. Railway has no GPUs, so models run on CPU. For larger models, add an OpenAI-compatible API key.

Are there licence terms to know?

Yes. The licence has a branding clause that keeps the name and logo visible unless you meet one of its exceptions. Read the upstream licence before rebranding.

How do I upgrade?

Images are pinned. Back up Postgres and the data volume, change the Open WebUI tag and redeploy; migrations run on start.

Guides

Similar apps

Tracklayer maintains the templates marked as such; Open WebUI is a trademark of its owners and this site is not affiliated with them.