Plans

AnythingLLM VPS Plans Coming Soon

We are preparing VPS plans with AnythingLLM VPS pre-installed. Below are the resources the application needs to run smoothly.
Minimum
  • Processor 2 vCPU
  • Memory (RAM) 2 GB
  • NVMe storage 20 GB

Official minimum, for use with cloud language models. Requires an AVX2-capable processor.

Recommended
  • Processor 4 vCPU
  • Memory (RAM) 8 GB
  • NVMe storage 80 GB

For many documents, local embedding models and several concurrent users.

Get notified when plans launch

Contact our team to learn more about AnythingLLM VPS plans or to plan the right setup for your needs today.

Contact Us Browse Linux VPS plans
Use Cases

What Can You Do with AnythingLLM?

Make internal knowledge searchable and askable, with answers grounded in your documents.

Internal knowledge base

Upload policies, procedures and handbooks so employees find answers to their questions instantly.

Support assistant

Upload your product manuals and let your support team prepare answers based on them.

Contract and document analysis

Summarize long contracts and reports and quickly find specific clauses and dates.

Workspaces per team

Keep each department’s documents in its own workspace and manage access per user.

Website chat widget

Embed a chat widget on your website that answers from your documents.

AI agents

Run tasks such as web search and file operations automatically with agents.

Why TRVDS for AnythingLLM VPS?

Your application runs in our data center in Bursa, Turkey, on resources reserved for you alone.

Pre-installed

The application is installed automatically after your server is created. No need to deal with Docker or dependencies.

Dedicated resources

Intel Xeon Gold processors, DDR4 RAM and NVMe storage. CPU and memory are not shared with other customers.

DDoS protection and unlimited traffic

DDoS protection with 40 Gbps capacity and unlimited traffic are included in every VPS plan.

Full control

With root access you can update the application, add a domain and SSL, and install other services alongside it.

What Is AnythingLLM?

AnythingLLM is an open-source application that lets you query your documents with AI. You upload PDFs, Word files, text files and web pages; their content is processed into a vector database, and questions are answered from these documents with sources cited. This approach is called RAG (Retrieval-Augmented Generation).

Documents are organized into workspaces. For example, HR policies, product manuals and contracts can be kept in separate workspaces, and each team only accesses the information in its own workspace.

Document AI on Your Own Server

The server edition of AnythingLLM is multi-user: administrators create users and decide who can see each workspace. Thanks to the built-in vector database, there is no extra service to install. AI agents can run tasks such as web search or file creation, and an embeddable chat widget is available for your website.

Your documents and vector database are stored on your server in Bursa, Turkey. When you use a cloud language model, only the document excerpts relevant to the question are sent to the provider.

Licensing and Resources

AnythingLLM is MIT licensed and free, including for commercial use. It works with cloud providers such as OpenAI and Anthropic, as well as local models through Ollama.

The official minimum is 2 vCPU and 2 GB RAM, and the processor must support AVX2; the Intel Xeon Gold processors in our servers do. For many documents, local embedding models or several concurrent users, we recommend 4 vCPU and 8 GB RAM. Storage needs grow with the amount of documents you upload.

Other Server Options

Looking for a different server?

Compare our other server options by operating system, control panel or resources.
FAQ

Frequently Asked Questions About AnythingLLM VPS

Check the most frequently asked questions and find answers instantly.

Yes. AnythingLLM is MIT licensed and free, including for commercial use. If you use a cloud language model, API usage is billed by the provider.

You can upload PDF, Word (DOCX), text and Markdown files, and add the content of web pages by providing a link.

Uploaded documents and the vector database are stored on your own server. When you use a cloud model, only the document excerpts relevant to the question are sent to the provider.

Yes. The server edition has a multi-user mode; you can create users and decide which workspaces each of them can access.

The official minimum is 2 vCPU, 2 GB RAM and an AVX2-capable processor. For many documents and local embedding models, we recommend 4 vCPU and 8 GB RAM.

Open WebUI is a general-purpose AI chat interface. AnythingLLM focuses on organizing your documents into workspaces and producing answers based on them, with sources cited.