AnythingLLM

anythingllm.com

Visit Website

An all-in-one desktop and self-hosted web app for chatting with your documents using any LLM, with a built-in RAG pipeline, multi-user workspaces, and support for local or cloud models.

Why it is useful

Packages the full RAG stack — document ingestion, vector storage, retrieval, and chat — into a single installable application that works with local models through Ollama or any OpenAI-compatible API. For teams that want a private ChatGPT-with-documents setup without building the infrastructure themselves, it eliminates weeks of integration work.