mintplex-labs/anything-llm

AnythingLLM is an all-in-one AI application that lets you build your own private ChatGPT-style assistant that can chat with your documents, run automated tasks, and connect to dozens of different AI models, all without sharing your data with a third party. The problem it addresses is that most AI tools are cloud-only, require technical setup, and don't let you control which AI model runs underneath. AnythingLLM gives you a polished, user-friendly interface while keeping everything configurable and optionally entirely local on your own machine. The way it works is you upload documents in formats like PDF, Word, or plain text into workspaces, and the app indexes them so the AI can search through them when answering your questions, a technique called retrieval-augmented generation (RAG). You can connect it to virtually any AI provider, including OpenAI, Anthropic, Google Gemini, Mistral, Ollama for local models, LM Studio, Groq, and many more. The app also supports AI agents that can browse the web, execute code, and perform multi-step tasks. Multi-user support with permission controls is available through the Docker version. For businesses, there is an embeddable chat widget you can drop into any website. The tech stack is JavaScript on the frontend, with a Node.js backend, and it runs comfortably as a Docker container or as a desktop application on Mac, Windows, and Linux. A full developer API lets you integrate AnythingLLM into other tools. You would choose AnythingLLM when you want a fully featured, privacy-conscious AI assistant for your organization's documents without being locked into a single AI provider or a managed cloud service.