Skip to content
Sign up Log in
One-click app

AnythingLLM Server

Chat with your own documents: AnythingLLM sorts PDFs, texts and web pages into workspaces and answers questions about them – on your server, installed with one click in the panel.

Choose Package Configure Server

Monthly cancellable · no setup fee · prepaid

Recommended spec

The optimal configuration

Our recommendation for AnythingLLM: the cheapest package with the right resources – no minimum term.

1
CPU Cores
AMD EPYC vCores
4GB
Memory
DDR4 ECC
20GB
NVMe Storage
NVMe SSD · Ceph HA
4,99€
Price
Monthly

Minimum requirements of AnythingLLM (below them the panel refuses the install): 2 GB RAM · 10 GB NVMe

In Detail

Why AnythingLLM on Your Own Server?

Your documents stay on your server in Frankfurt; only the text snippets needed for an answer go to the AI provider. You decide which model that is – and can switch at any time.

AnythingLLM is an open-source application that lets you load documents into workspaces and ask questions about them using retrieval-augmented generation (RAG). Answers come from a language model of your choice, for example from OpenAI, Anthropic or another connected provider; AnythingLLM already ships with a vector database and embedding. On top of that there are agents that can, for example, fetch web pages or summarise documents. The panel installs AnythingLLM in single-user mode, protected by a generated password – there is no open interface without a password. Telemetry is switched off during the install. If you like, the panel sets up your domain with HTTPS, now or later. Plan for at least 2 GB of RAM and more storage if you add many documents.

  • DDoS Protection
  • Location — Frankfurt DE-CIX
  • Storage — NVMe Ceph HA

Features

All Benefits at a Glance

Full root access — install anything

Install any software, any runtime, any version — no restrictions from panels or shared hosting.

NVMe SSD Ceph HA storage

High-performance NVMe SSDs in a Ceph HA cluster for maximum I/O performance and 3x redundancy.

Full SSH root access

Connect anytime via SSH and manage your server with full administrator privileges.

Enterprise DDoS protection included

Permanent protection with high-capacity filtering — included free with every server.

Runs continuously — no sleep mode

No sleep mode and no shutdown when idle: your server keeps running as long as its term is paid.

Low latency — Frankfurt DE-CIX

Located directly at DE-CIX in Frankfurt for low latency to European networks.

Always included

Included with every root server

Enterprise DDoS protection included Full root access — install anything NVMe SSD Ceph HA storage Runs continuously — no sleep mode Low latency — Frankfurt DE-CIX 1× IPv4 + /64 IPv6

All Root Server Packages

Choose the package that best fits your project

Every one of these packages meets the minimum requirements of AnythingLLM.

RootPaket-1

Recommended

4,99€ Monthly

  • 1 AMD EPYC vCores
  • 4 GB DDR4 RAM
  • 20 GB NVMe SSD
  • 1× IPv4 + /64 IPv6
  • DDoS Protection Included
View Packages

RootPaket-2

5,99€ Monthly

  • 2 AMD EPYC vCores
  • 6 GB DDR4 RAM
  • 50 GB NVMe SSD
  • 1× IPv4 + /64 IPv6
  • DDoS Protection Included
View Packages

RootPaket-3

9,99€ Monthly

  • 4 AMD EPYC vCores
  • 16 GB DDR4 RAM
  • 80 GB NVMe SSD
  • 1× IPv4 + /64 IPv6
  • DDoS Protection Included
View Packages

RootPaket-4

19,69€ Monthly

  • 6 AMD EPYC vCores
  • 24 GB DDR4 RAM
  • 130 GB NVMe SSD
  • 1× IPv4 + /64 IPv6
  • DDoS Protection Included
View Packages

RootPaket-5

30,49€ Monthly

  • 8 AMD EPYC vCores
  • 32 GB DDR4 RAM
  • 180 GB NVMe SSD
  • 1× IPv4 + /64 IPv6
  • DDoS Protection Included
View Packages

RootPaket-6

46,79€ Monthly

  • 8 AMD EPYC vCores
  • 48 GB DDR4 RAM
  • 200 GB NVMe SSD
  • 1× IPv4 + /64 IPv6
  • DDoS Protection Included
View Packages

Get Started in 3 Steps

Get Started in 3 Steps

1

Order a root server with at least 2 GB of RAM

2

Pick AnythingLLM under “Apps” in the panel, optionally enter a domain

3

Log in with the password from the panel and choose your AI provider and model

  • Admin account created during the install
  • Own domain with HTTPS (Let’s Encrypt) possible
  • The install usually takes about 3 minutes
  • Runs on Ubuntu, Debian, AlmaLinux and Rocky Linux

More one-click apps: Open WebUI + Ollama · LobeChat · Langflow · LibreChat · WordPress · Nextcloud · Vaultwarden · Coolify · Jellyfin · Forgejo / Gitea

Frequently Asked Questions

Answers to the most important questions

Which files can I upload?
Among others PDF, Word documents, text and Markdown files; web pages can be pulled in via link. AnythingLLM splits the content and stores it in its built-in vector database.
Do I need an API key?
For cloud models such as OpenAI or Anthropic, yes – you enter it after logging in. Alternatively you connect your own model server, such as Ollama on a more powerful machine.
Can several people use AnythingLLM?
The install uses single-user mode with one password. In AnythingLLM’s settings you can switch to multi-user mode and create accounts with their own roles.
How much RAM do I need?
At least 2 GB, because AnythingLLM reads documents and turns them into vectors itself. For large document collections pick a package with more RAM and storage.

Get Started Now

Your documents, your AI, your server – from €4.99 a month.

Choose Package Configure Server