anythingllm v0.1.0

AnythingLLM — an all-in-one AI application: chat with your documents (RAG), connect any LLM (Ollama, OpenAI, Anthropic, …) and vector database, and organize work into workspaces with agents. Deployed as a host-networked Nomad service with a persistent storage volume.

nomad-pack run anythingllm --registry nomploy

…or one line (add registry + run)

curl -fsSL https://packs.nomploy.com/install.sh | sh -s -- anythingllm

Needs nomad-pack on PATH. The script only adds the nomploy registry and runs this pack.

Source ↗ Project ↗ ★ 66.4k ⚑ Report an issue

2 tasks http 3001 1 volume image mintplexlabs/anythingllm:latest tracks :latest image bumped today

Variables 8

values.hcl

Save as values.hcl, edit, then run:

nomad-pack run anythingllm -f values.hcl --registry nomploy

# The name of the Nomad job.
job_name = "anythingllm"

# The Nomad namespace to deploy into.
namespace = "default"

# The datacenters to deploy to.
datacenters = ["*"]

# The AnythingLLM container image. Pin a tag in production.
image = "mintplexlabs/anythingllm:latest"

# Host port for the AnythingLLM web UI / API. The container listens on 3001.
port = 3001

# Named volume for AnythingLLM storage (/app/server/storage): the SQLite DB, vector cache, and documents.
storage_volume = "anythingllm_storage"

# Placement constraints. Pin to the node holding the volume. On a nomploy cluster: attribute = "$${meta.nomploy_control_plane}", operator = "=", value = "true".
constraints = []

# Resources for the AnythingLLM task.
resources = {
    cpu    = 1000
    memory = 1024
  }

Name	Type	Default	Description
job_name	string	"anythingllm"	The name of the Nomad job.
namespace	string	"default"	The Nomad namespace to deploy into.
datacenters	list	["*"]	The datacenters to deploy to.
image	string	"mintplexlabs/anythingllm:latest"	The AnythingLLM container image. Pin a tag in production.
port	number	3001	Host port for the AnythingLLM web UI / API. The container listens on 3001.
storage_volume	string	"anythingllm_storage"	Named volume for AnythingLLM storage (/app/server/storage): the SQLite DB, vector cache, and documents.
constraints	list	[]	Placement constraints. Pin to the node holding the volume. On a nomploy cluster: attribute = "$${meta.nomploy_control_plane}", operator = "=", value = "true".
resources	object	{ cpu = 1000 memory = 1024 }	Resources for the AnythingLLM task.

Back up this pack

This pack stores data in one Docker named volume: anythingllm_storage

restic

# Run on the node hosting this pack. Point restic at your repo first:
#   export RESTIC_REPOSITORY="s3:https://<account>.r2.cloudflarestorage.com/<bucket>"
#   export RESTIC_PASSWORD="<repo-password>"
#   export AWS_ACCESS_KEY_ID=<key>  AWS_SECRET_ACCESS_KEY=<secret>
restic backup \
  /var/lib/docker/volumes/anythingllm_storage/_data

rclone (sync to S3/R2)

rclone sync /var/lib/docker/volumes/anythingllm_storage/_data backup:<bucket>/anythingllm_storage

Paths assume the default Docker volume location (/var/lib/docker/volumes). Restore by stopping the job, restoring files into the same volume, and re-running the pack.

Readme

anythingllm

AnythingLLM — an all-in-one AI application for chatting with your documents. Connect any LLM (Ollama, OpenAI, Anthropic, local models…) and vector database, upload documents for retrieval-augmented chat (RAG), and organize everything into workspaces with agents and a built-in API.

Single host-networked Nomad service with a persistent storage volume. A prestart task chowns the volume so the app (uid 1000) can write it, and SYS_ADMIN is added for the document collector.

Deploy

nomad-pack registry add nomploy https://github.com/Nomploy/nomad-packs
nomad-pack run anythingllm --registry=nomploy

Configure

Variable	Default	Description
`port`	`3001`	Web UI / API port (`SERVER_PORT`).
`storage_volume`	`anythingllm_storage`	`/app/server/storage` — SQLite DB, vector cache, uploaded documents.
`image`	`mintplexlabs/anythingllm:latest`	Container image. Pin a tag in production.
`resources`	`{ cpu = 1000, memory = 1024 }`	Task resources.

On first run, a setup wizard walks you through choosing an LLM provider and embedding/vector settings. For a fully local stack, point it at the co-located ollama pack (http://127.0.0.1:11434) and the chroma or qdrant packs, then create a workspace and upload documents. Serves plain HTTP — front it with a reverse proxy for TLS. Pin the job to the node holding the volume with constraints.