AnythingLLM

What's included

AnythingLLM is a private AI assistant that runs locally on the user's device, with no required accounts, mandatory API keys, or vendor-set token limits. It lets users connect local models (via Ollama, LM Studio, etc.) or cloud providers of their choice. Key features include chatting with documents (local RAG), building custom agents, managing multiple isolated workspaces, and keeping history entirely on-device, without sending data to AnythingLLM's servers. The software is open source and free for individual use; a hosted cloud and team version with paid plans for managed hosting is also available.