Self-host LibreChat on a VPS
A self-hosted ChatGPT-style interface for many model providers, with agents, search, and multi-user login.
levelrail-cli templates deploy librechat --name my-librechatSpecification
- Status
- Listed
- Category
- AI
- Services
- librechat, meilisearch, mongo
- Ports
- 3080
- Volumes
- 3
- Memory
- about 2 GiB
- arm64
- image published
- amd64
- image published
- Settings to fill in
- none
- License
- Permissive license, MIT
About LibreChat
A self-hosted ChatGPT-style interface for many model providers, with agents, search, and multi-user login. Runs 3 containers (librechat, meilisearch, mongo), with librechat listening on port 3080; data is kept in named volumes.
What it deploys
LibreChat runs as 3 services in a single Compose app, listening on port 3080, with 3 named volume mounts.
| Service | Image | Tag | Ports | Volumes |
|---|---|---|---|---|
| librechat | ghcr.io/danny-avila/librechat | v0.8.7 | 3080 | librechat_images -> /app/client/public/images |
| meilisearch | getmeili/meilisearch | v1.54.0 | none | librechat_meili_data -> /meili_data |
| mongo | mongo | 7 | none | librechat_mongo_data -> /data/db |
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 3080 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. 6 secrets are generated at deploy and stored encrypted. Values are never shown here.
| Service | Variable | Value |
|---|---|---|
| librechat | ALLOW_REGISTRATION | Preset by the template |
| librechat | CREDS_IV | Generated at deploy |
| librechat | CREDS_KEY | Generated at deploy |
| librechat | DOMAIN_CLIENT | Preset by the template |
| librechat | DOMAIN_SERVER | Preset by the template |
| librechat | HOST | Preset by the template |
| librechat | JWT_REFRESH_SECRET | Generated at deploy |
| librechat | JWT_SECRET | Generated at deploy |
| librechat | MEILI_HOST | Preset by the template |
| librechat | MEILI_MASTER_KEY | Generated at deploy |
| librechat | MONGO_URI | Preset by the template |
| librechat | PORT | Preset by the template |
| meilisearch | MEILI_MASTER_KEY | Generated at deploy |
| meilisearch | MEILI_NO_ANALYTICS | Preset by the template |
Install LibreChat 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 librechat -
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 librechat --name my-librechat
Without a domain the app gets an sslip.io address. You can also deploy it from the dashboard: Apps, New app, Browse templates, then LibreChat.
Docs and upstream
More in AI
- LangfuseTrace, evaluate, and debug LLM applications with prompt management and cost analytics.
- LangflowA visual low-code tool for building and deploying multi-agent and RAG workflows in Python.
- Label StudioA flexible data labeling tool for text, images, audio, and video, with export to common ML formats.
- 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.
- Kokoro TTSA CPU text-to-speech server with an OpenAI-compatible /v1/audio/speech API, built on the Kokoro model. Apache-2.0 licensed. The image is about 3 GB and there is no login, so keep it on a private network or behind an auth proxy.
- LiteLLM ProxyOne OpenAI-format gateway in front of 100+ model providers, with keys, budgets, and spend tracking.