AnythingLLM: full local RAG with web UI and embedded vector DB
In one sentence AnythingLLM delivers a full-stack RAG system with a web interface, Ollama/LocalAI LLM backend support, and an embedded vector database, all offline in a single container.
privateGPT had shown that local RAG was possible, but still required the command line and had no user interface. AnythingLLM takes local RAG to the next level: a real web application with separate workspaces, drag-and-drop document loading, multi-user management, and a choice of LLM backend.
You can connect it to Ollama, LocalAI, or even a remote OpenAI API, and switch backends without recreating your workspaces. Documents are indexed and stay on your server, whether it's a home PC or a company server.
For anyone who wants to build a private corporate knowledge base or a document assistant without touching the cloud, AnythingLLM is among the most complete open source projects available.
Companies
Mintplex Labs
Tools
AnythingLLM, Ollama, LocalAI
Tags
Sources