Self-host Lobe Chat with Docker
A modern, open-source AI chat framework supporting many model providers.
This page describes the Levelrail template for Lobe Chat (AI). It deploys the services below as one Docker Compose app on your own server.
Project site: https://lobehub.com/docs/self-hosting/start.Recommended memory: about 512 MiB.
Services, ports and volumes
| Service | Image | Container ports | Volumes |
|---|---|---|---|
lobe-chat | lobehub/lobe-chat:1.135.5 | 3210 | none |
Environment variables
| Service | Variable | Value |
|---|---|---|
lobe-chat | ACCESS_CODE | Generated at deploy |
lobe-chat | OPENAI_API_KEY | Preset in the template |
lobe-chat | OPENAI_PROXY_URL | Preset in the template |
Passwords and keys marked as generated are created for you when the app is deployed and stored as secrets. Values are not shown here.
Deploy Lobe Chat with Levelrail
In the dashboard, open Apps, choose New app, then Browse templates, and select Lobe Chat. Review the Compose body and deploy.
With the CLI:
levelrail-cli templates deploy lobe-chat --name my-lobe-chatSee Service template catalog for how templates work, and Getting started if you have not installed Levelrail yet.
More AI templates
All templates are listed in the self-host gallery.