AnythingLLM
All-in-one private chat with your documents, agents and an embeddable widget.
Quick answer
AnythingLLM is an all-in-one private chat with your documents, agents and an embeddable widget, listed under Knowledge base & RAG. A typical small-business use: small-team "chat with our files" workspace without a complex stack. Official hardware: minimum 2 vCPU · 2 GB RAM · 5 GB disk. That fits a Hetzner Cloud CPX22 server at about €19.99/month (server only, excl. VAT). License: MIT, which allows internal business use.
Last updated · facts verified against official docs on · sources
Activity data comes from GitHub and was last refreshed Oct 22, 2026.
What is AnythingLLM?
AnythingLLM bundles document chat (RAG), agents, MCP tools and a built-in vector database in one app. It can use hosted models or run local models on CPU or GPU. The Docker version adds multi-user permissions and an embeddable website chat widget.
Where it fits in a 10–200 person business
- Small-team "chat with our files" workspace without a complex stack
- Website chat widget answering from your own content
- Private assistant on a laptop or a small VPS
These use cases are our editorial suggestions, not claims made by the project.
Can a business use AnythingLLM? (license)
| License | MIT |
|---|---|
| Type | Permissive: MIT / Apache-2.0: use, modify and sell with few obligations. |
| Internal business use | Allowed under the license text |
| What to watch | Permissive. Internal and commercial use allowed; keep the copyright notice. |
This is a plain-English summary of the license text, not legal advice. Third-party models you run with it have their own licenses.
What hardware does AnythingLLM need?
| Minimum | 2 vCPU · 2 GB RAM · 5 GB disk |
|---|---|
| Recommended | Not published |
The CPU must support AVX2. That is the one hard hardware requirement.
Source: docs.anythingllm.com/installation-docker/system-requirements
How much does it cost to host AnythingLLM per month?
| Minimum spec | 2 vCPU · 2 GB RAM · 5 GB disk → CPX22 (2 vCPU, 4 GB, 80 GB disk) €19.99/mo |
|---|
How we got this: we took the cheapest Hetzner Cloud Regular Performance (shared AMD vCPU) plan with at least the RAM and vCPU the project lists, using prices read from www.hetzner.com/cloud/regular-performance on 2026-10-22. "From" monthly price cap shown by Hetzner, excluding VAT. Prices vary by location. Covers the server only; it excludes LLM API usage, backups, extra storage, GPUs and your time. Disk is not matched; add a volume if you need more than the plan includes.
How to deploy AnythingLLM
Method: Docker
export STORAGE_LOCATION=$HOME/anythingllm && mkdir -p $STORAGE_LOCATION && \
touch "$STORAGE_LOCATION/.env" && \
docker run -d -p 3001:3001 --cap-add SYS_ADMIN \
-v ${STORAGE_LOCATION}:/app/server/storage \
-v ${STORAGE_LOCATION}/.env:/app/server/.env \
-e STORAGE_DIR="/app/server/storage" \
mintplexlabs/anythingllmFrom the official instructions: github.com/Mintplex-Labs/anything-llm/blob/master/docker/HOW_TO_USE_DOCKER.md. Always check the source for the current version before you run it.
Known gotchas when self-hosting AnythingLLM
- Without AVX2 the server crashes with "Illegal instruction" when LanceDB loads. Proxmox/QEMU default CPU types (kvm64, x86-64-v2) hide AVX2; set the VM CPU type to "host". source
- Multi-user permissions and the embeddable chat widget are only available in the Docker version, not the desktop app. source
Alternatives in Knowledge base & RAG
- RAGFlow RAG engine with deep document parsing (OCR, layout and tables) and cited answers. Compare AnythingLLM vs RAGFlow
- PrivateGPT API-first private document Q&A that sits on top of your own LLM server. Compare AnythingLLM vs PrivateGPT
- Onyx (formerly Danswer) AI chat and enterprise search connected to 50+ workplace apps. Compare AnythingLLM vs Onyx (formerly Danswer)
- FastGPT Knowledge-base Q&A and visual AI workflow platform. Compare AnythingLLM vs FastGPT
- MaxKB Enterprise knowledge-base and agent platform with RAG and workflows. Compare AnythingLLM vs MaxKB
AnythingLLM FAQ
How much RAM does AnythingLLM need?
The official minimum is 2 vCPU · 2 GB RAM · 5 GB disk. The CPU must support AVX2. That is the one hard hardware requirement.
How much does it cost to self-host AnythingLLM?
The software is free to download. Based on the official minimum 2 vCPU · 2 GB RAM · 5 GB disk: That fits a Hetzner Cloud CPX22 server at about €19.99/month (server only, excl. VAT). That covers the server only, not LLM API usage, backups, extra storage or your time.
Is AnythingLLM free for commercial use?
AnythingLLM is licensed under MIT (Permissive). Internal business use is allowed under the license text. Permissive. Internal and commercial use allowed; keep the copyright notice. This is a summary, not legal advice.
What are common problems when self-hosting AnythingLLM?
Without AVX2 the server crashes with "Illegal instruction" when LanceDB loads. Proxmox/QEMU default CPU types (kvm64, x86-64-v2) hide AVX2; set the VM CPU type to "host". Multi-user permissions and the embeddable chat widget are only available in the Docker version, not the desktop app.
Is AnythingLLM still maintained?
Yes, it is actively developed. Last commit: Oct 22, 2026. Latest release: v1.18.0 (Oct 13, 2026). Checked Oct 22, 2026.
How do I install AnythingLLM?
The official method is Docker. The exact commands are in the "How to deploy" section above and in the official instructions: https://github.com/Mintplex-Labs/anything-llm/blob/master/docker/HOW_TO_USE_DOCKER.md
What are self-hosted alternatives to AnythingLLM?
Other apps in Knowledge base & RAG: RAGFlow, PrivateGPT, Onyx (formerly Danswer), FastGPT, MaxKB.
Sources
- GitHub repository: github.com/Mintplex-Labs/anything-llm
- Official documentation, Hardware requirements, Gotcha 1: docs.anythingllm.com/installation-docker/system-requirements
- License text: github.com/Mintplex-Labs/anything-llm/blob/master/LICENSE
- Deploy instructions: github.com/Mintplex-Labs/anything-llm/blob/master/docker/HOW_TO_USE_DOCKER.md
- Gotcha 2: github.com/Mintplex-Labs/anything-llm#readme
- Hetzner Cloud pricing (cost estimate): www.hetzner.com/cloud/regular-performance
- GitHub stars, commits and releases: GitHub REST API, fetched
Facts on this page were checked against the project's own repository and docs on 2026-10-22. Spotted something out of date? Tell us.