AnythingLLM

AnythingLLM is an all-in-one AI app for building a private, ChatGPT-style workspace. Connect a local or cloud LLM, ingest your documents, and start chatting in minutes, with everything running locally by default and no configuration required to get going.

Document pipelines and built-in vector databases power chat with source citations, while agents can browse the web and run tasks inside your workspace. A no-code agent builder, dynamic model routing, memories, scheduled tasks, and MCP support extend it further, and multi-user access with per-user permissioning keeps shared instances secure.

Desktop apps run on Windows, macOS, and Linux, and the same app deploys as a Docker container or to any cloud. A developer API and an embeddable chat widget let you wire AnythingLLM into your own products.