Self-host AnythingLLM with Docker
A private chat workspace over your documents, with built-in RAG and support for local or hosted models.
This page describes the Levelrail template for AnythingLLM (AI). It deploys the services below as one Docker Compose app on your own server.
Project site: https://docs.anythingllm.com.Recommended memory: about 2048 MiB.
Services, ports and volumes
| Service | Image | Container ports | Volumes |
|---|---|---|---|
anythingllm | mintplexlabs/anythingllm:1.16.2 | 3001 | anythingllm_storage -> /app/server/storage |
Environment variables
| Service | Variable | Value |
|---|---|---|
anythingllm | JWT_SECRET | Generated at deploy |
anythingllm | SERVER_PORT | Preset in the template |
anythingllm | STORAGE_DIR | 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 AnythingLLM with Levelrail
In the dashboard, open Apps, choose New app, then Browse templates, and select AnythingLLM. Review the Compose body and deploy.
With the CLI:
levelrail-cli templates deploy anythingllm --name my-anythingllmSee 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.