Self-host AnythingLLM with Levelrail
A private chat workspace over your documents, with built-in RAG and support for local or hosted models.
- AuthorMintplex-Labs
- LicenceMIT
- Memory2 GiB
- Archarm64
- Services1
How to self-host AnythingLLM
-
Pull the images
One image is pulled on your server.
Show images
mintplexlabs/anythingllm:1.16.2
-
Create the app
One service starts in a single Compose app, with 1 named volume mount for your data, on port 3001.
-
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.
AnythingLLM requirements
- Memory
- About 2 GiB
- Architectures
- amd64 image published, arm64 image published
- Ports
- 3001
- Domain
- Optional, an sslip.io address is used without one
- Settings
- none to fill in
- License
- MIT, permissive license
- Listed. It is in the catalog but not verified. Back up the data volume before changing an image tag.
- Host ports. It publishes port 3001 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 AnythingLLM. 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 AnythingLLM docs page.
Deploy AnythingLLM your way
Every format below deploys the same pinned images. Pick the one that fits how you work.
Deploy AnythingLLM from the CLI
levelrail-cli templates deploy anythingllm --name my-anythingllm Deploy AnythingLLM with the API
curl -X POST -H "Authorization: Bearer $TOKEN" \
https://levelrail.example.com/api/v1/service-templates/anythingllm/deploy AnythingLLM configuration
AnythingLLM services
| Service | Image | Ports | Volumes |
|---|---|---|---|
| anythingllm | mintplexlabs/anythingllm:1.16.2 | 3001 | anythingllm_storage -> /app/server/storage |
AnythingLLM environment variables
| Variable | Service | Value |
|---|---|---|
| JWT_SECRET | anythingllm | Generated at deploy |
| SERVER_PORT | anythingllm | Preset by the template |
| STORAGE_DIR | anythingllm | Preset by the template |
Ports and volumes
- Ports
- 3001
- Volumes
- 1 named mount: anythingllm_storage -> /app/server/storage
AnythingLLM FAQ
How much memory does AnythingLLM need?
The catalog lists about 2 GiB of memory for AnythingLLM.
Does AnythingLLM run on arm64?
For AnythingLLM, an arm64 image is published; amd64 is image published.
What licence is AnythingLLM under?
AnythingLLM is licensed under MIT, which is permissive, with few conditions on reuse.
Does AnythingLLM need configuration before it starts?
No. The template fills in its own defaults and generates secrets at deploy time.
Which ports does AnythingLLM use?
AnythingLLM listens on port 3001 inside the stack.
Where does AnythingLLM keep its data?
In a named volume: anythingllm_storage mounted at /app/server/storage.
Can I deploy AnythingLLM 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 anythingllm for this app, so check that entry as well. Dokku deploys container images with its own commands, so the pinned image mintplexlabs/anythingllm:1.16.2 is what you deploy there.