Self-host Lobe Chat with Levelrail
A modern, open-source AI chat framework supporting many model providers.
- Authorlobehub
- LicenceLicenseRef-LobeHub-Community
- Memory512 MiB
- Archarm64
- Services1
How to self-host Lobe Chat
-
Pull the images
One image is pulled on your server.
Show images
lobehub/lobe-chat:1.135.5
-
Create the app
One service starts in a single Compose app, on port 3210.
-
Fill in the secrets
1 secret is generated and stored encrypted, 2 settings are preset, you do not have to fill in anything.
-
Open it
Without a domain the app gets an sslip.io address; add --domain SERVICE=HOST to use your own.
Lobe Chat requirements
- Memory
- About 512 MiB
- Architectures
- amd64 image published, arm64 image published
- Ports
- 3210
- Domain
- Optional, an sslip.io address is used without one
- Settings
- none to fill in
- License
- LicenseRef-LobeHub-Community, source available
- Listed. It is in the catalog but not verified. Back up the data volume before changing an image tag.
- Host ports. It publishes port 3210 on the host, so open them in the VPS firewall only if you want that.
Install Levelrail first
On a server with Levelrail running, run the command above, or open the dashboard: Apps, New app, Browse templates, then Lobe Chat. New to Levelrail? Install it on a fresh VPS first.
docker pull ghcr.io/glincker/levelrail:latest Then levelrail-cli login --device. See Getting started and the Lobe Chat docs page.
Deploy Lobe Chat your way
Every format below deploys the same pinned images. Pick the one that fits how you work.
Deploy Lobe Chat from the CLI
levelrail-cli templates deploy lobe-chat --name my-lobe-chat Deploy Lobe Chat with the API
curl -X POST -H "Authorization: Bearer $TOKEN" \
https://levelrail.example.com/api/v1/service-templates/lobe-chat/deploy Lobe Chat configuration
Lobe Chat services
| Service | Image | Ports | Volumes |
|---|---|---|---|
| lobe-chat | lobehub/lobe-chat:1.135.5 | 3210 | none |
Lobe Chat environment variables
| Variable | Service | Value |
|---|---|---|
| ACCESS_CODE | lobe-chat | Generated at deploy |
| OPENAI_API_KEY | lobe-chat | Preset by the template |
| OPENAI_PROXY_URL | lobe-chat | Preset by the template |
Ports and volumes
- Ports
- 3210
- Volumes
- none
Lobe Chat FAQ
How much memory does Lobe Chat need?
The catalog lists about 512 MiB of memory for Lobe Chat.
Does Lobe Chat run on arm64?
For Lobe Chat, an arm64 image is published; amd64 is image published.
What licence is Lobe Chat under?
Lobe Chat is licensed under LicenseRef-LobeHub-Community, which is source-available, so read the terms before commercial use.
Does Lobe Chat need configuration before it starts?
No. The template fills in its own defaults and generates secrets at deploy time.
Which ports does Lobe Chat use?
Lobe Chat listens on port 3210 inside the stack.
Can I deploy Lobe Chat on Dokploy or Dokku?
The services and pinned images on this page can be run on any Docker host. The public Dokploy templates list has an entry with the id lobe-chat for this app, so check that entry as well. Dokku deploys container images with its own commands, so the pinned image lobehub/lobe-chat:1.135.5 is what you deploy there.