Self-host Lobe Chat on a VPS
A modern, open-source AI chat framework supporting many model providers.
levelrail-cli templates deploy lobe-chat --name my-lobe-chatSpecification
- Status
- Listed
- Category
- AI
- Services
- lobe-chat
- Ports
- 3210
- Volumes
- 0
- Memory
- about 512 MiB
- arm64
- image published
- amd64
- image published
- Settings to fill in
- none
About Lobe Chat
Optional: set OPENAI_API_KEY (and OPENAI_BASE_URL for a compatible endpoint) to preconfigure a provider. Users can also add keys in the app's settings.
What it deploys
Lobe Chat runs as one service in a single Compose app, listening on port 3210.
| Service | Image | Tag | Ports | Volumes |
|---|---|---|---|---|
| lobe-chat | lobehub/lobe-chat | 1.135.5 | 3210 | none |
Before you install
- CPU architecture. arm64 listed. Every image lists linux/arm64 in its registry manifest. That is a manifest fact, not proof the app runs on Arm.
- Listed. It is in the catalog. Back up the data volume before changing an image tag.
- Host ports. It publishes port 3210 directly on the host, so open them in the VPS firewall only if you want that.
Settings and environment
You do not have to fill in anything. 1 secret is generated at deploy and stored encrypted. Values are never shown here.
| Service | Variable | Value |
|---|---|---|
| lobe-chat | ACCESS_CODE | Generated at deploy |
| lobe-chat | OPENAI_API_KEY | Preset by the template |
| lobe-chat | OPENAI_PROXY_URL | Preset by the template |
Install Lobe Chat on a VPS
-
Install Levelrail on a fresh VPS
Run this as root on a Linux server (amd64 or arm64) with ports 80 and 443 reachable. The installer prints a setup link.
curl -fsSL https://levelrail.com/install.sh | sudo sh -
Sign in
Open the setup link, choose a password, then log the CLI in. The CLI install command is
curl -fsSL https://levelrail.com/install-cli.sh | shif the machine does not have it. See Getting started.levelrail-cli login --device -
Read the template
Shows the entry, including its full compose.yaml.
levelrail-cli templates get lobe-chat -
Deploy it
This deploys the template compose file as an app. The app name defaults to the template id; --name sets another.
levelrail-cli templates deploy lobe-chat --name my-lobe-chat
Without a domain the app gets an sslip.io address. You can also deploy it from the dashboard: Apps, New app, Browse templates, then Lobe Chat.
Docs and upstream
More in AI
- LocalAIA drop-in OpenAI-compatible API that runs language, image, and speech models on your own hardware.
- llama.cpp ServerThe llama.cpp HTTP server: run quantized GGUF models on plain CPUs with an OpenAI-compatible API.
- LiteLLM ProxyOne OpenAI-format gateway in front of 100+ model providers, with keys, budgets, and spend tracking.
- LightRAGGraph based retrieval augmented generation server with a web UI and API. Runs on local file storage; point it at a model provider with the LLM and embedding settings.
- LibreChatA self-hosted ChatGPT-style interface for many model providers, with agents, search, and multi-user login.
- LangfuseTrace, evaluate, and debug LLM applications with prompt management and cost analytics.