What is AnythingLLM?
AnythingLLM is a full-stack, self-hostable application that lets you chat with any document, URL, or content using an LLM of your choice. It is designed to be the easiest possible path to a private ChatGPT for your data.
Key Features
- Multi-user support — Create workspaces with different documents for different users.
- Any LLM — OpenAI, Anthropic, Google, Ollama, LM Studio, LocalAI — plugs into anything.
- Any document — PDF, DOCX, TXT, URLs, YouTube transcripts, GitHub repos, Confluence, Notion.
- Built-in vector database — Ships with LanceDB; swap for Chroma, Qdrant, Pinecone.
- Agent mode — Web browsing, code execution, chart generation.
- Desktop app — Electron app for Mac/Windows/Linux. No Docker required.
Quick Start (Docker)
docker pull mintplexlabs/anythingllm
docker run -d -p 3001:3001 \
--cap-add SYS_ADMIN \
-v ${PWD}/anythingllm:/app/server/storage \
mintplexlabs/anythingllm
Why AnythingLLM over Dify/Flowise?
AnythingLLM is the most user-friendly out of the box. No setup, no visual builder — upload documents and start chatting. If you want to build custom AI workflows, use Dify. If you just want a private ChatGPT for your files, AnythingLLM wins.