AnythingLLM hosting
A private document workspace — drop files in, ask questions, get cited answers.
AnythingLLM hosting at AIHostBox means a dedicated, single-tenant AnythingLLM instance on our infrastructure: we install it, pin it to a reviewed release, put it behind TLS on your domain, back it up nightly and keep it patched. Plans start at $18.99 per month and the admin account, the data and any API keys are yours.
AnythingLLM is the shortest route from a folder of documents to a working knowledge assistant. You create a workspace, upload PDFs, Word files, spreadsheets or a website crawl, and ask questions; answers come back with citations to the source chunk. Workspaces keep separate document sets and permissions, so sales and legal do not share a context window.
Embedding and vector storage are built in, so a single plan covers the whole pipeline. It works with commercial model APIs and with local endpoints, which means the documents and the answers can both stay inside infrastructure you control.
AnythingLLM hosting plans
Every plan is a dedicated single-tenant instance with NVMe storage, nightly off-box backups, TLS and managed patching. Quarterly, semi-annual and annual terms are discounted at checkout. Model tokens are not included — you bring your own key.
How we run AnythingLLM
One mintplexlabs/anythingllm container holding the server, the document collector and the embedded LanceDB vector store, with /app/server/storage on a persistent volume.
What we configure for you
- JWT_SECRET, SIG_KEY and SIG_SALT generated per instance
- STORAGE_DIR on a persistent, backed-up volume
- LLM_PROVIDER and EMBEDDING_ENGINE set to your provider or a local Ollama plan
- VECTOR_DB left on lancedb, or pointed at Qdrant, Milvus, Weaviate or pgvector
- DISABLE_TELEMETRY on unless you want usage reporting
- Password or multi-user mode enabled before the URL is shared
Which plan fits
Pro (8 GB) is the practical floor once PDFs are being parsed and embedded on the box, and handles a team with a few thousand documents. Max (12 GB) gives headroom for large imports, website crawls and the native embedder running alongside many active workspaces.
The honest limits
Chat quality depends on the model you connect; a small local model on CPU answers slowly and less precisely than a commercial API. Multi-user mode is a one-way switch.
What people run AnythingLLM for
Company knowledge base
Handbooks, contracts and specifications, answered with citations.
Client-specific workspaces
One workspace per client so contexts never bleed.
Research corpus
Ask questions across hundreds of papers at once.
Licence and version policy
| Item | Position |
|---|---|
| Upstream licence | MIT |
| Sold as managed hosting | Yes |
| Tenancy | Single tenant — one customer per instance |
| Patching | Critical advisories within 24 hours, high severity within 72 |
Our full position on licences, including the applications we decline to sell, is on the licensing page.
Reading on AnythingLLM
Works well with AnythingLLM
Ollama
Your private LLM server — pull a model, get an API, keep every token on your own box.
from $16.99/moDetails →
Qdrant
A fast vector database with real filtering, written in Rust.
from $5.99/moDetails →
Milvus
Vector search built for very large collections.
from $18.99/moDetails →
LiteLLM
One OpenAI-compatible endpoint in front of every model provider you use.
from $5.99/moDetails →More Agents & RAG we host
Dify
A visual studio for building LLM apps, agents and RAG pipelines.
from $18.99/moDetails →
Flowise
Drag-and-drop LLM flows, agents and chatbots you can embed anywhere.
from $11.99/moDetails →
Langflow
A visual builder for LangChain flows and multi-agent systems.
from $11.99/moDetails →
RAGFlow
Deep document understanding for RAG — tables, layouts and scanned pages.
from $36.99/moDetails →AnythingLLM hosting: your questions
Do I need a separate vector database?
Where do the embeddings run?
Can I give colleagues their own logins?
Which model providers does AnythingLLM support?
Is there an API for integrating it into other tools?
What exactly is in the backup?
Run AnythingLLM without running a server
A dedicated AnythingLLM instance, deployed and maintained by us. Month to month, cancel whenever.