AnythingLLM
Also: Anything LLM
A desktop app for chatting with your own documents using a local model.
The fuller definition
AnythingLLM is a desktop and server application for chatting with documents in workspaces. It has a built-in local engine and can connect to Ollama, LM Studio, and other providers.
- Workspace
Your documents
- AnythingLLM
Retrieval and chat
- Engine
Built-in or Ollama
A simplified relationship, not a screenshot or a complete design.
A concrete example
A lawyer creates a workspace for a fictional record, adds documents, and asks questions using a local model.
The distinction that matters
Document-chat convenience does not replace checking the passages the answer relies on.
Related terms
Open WebUI
A chat interface you can host yourself. It connects to a model service, which may be local or remote.
Documents & retrievalRAG — Retrieval-augmented generation
Letting the model look things up in your documents before answering, and show where the answer came from. Like an open-book exam.
Products & model familiesOllama
Software for downloading and running AI models. It can run local models, but you still need to check which model and service you chose.
Where it is taught
APIs and JSON: connect a model to a small programSource and further reading
MDN · Web technology glossaryThe definition and example are written for this library. The link gives background, official documentation or legal authority as labelled. Legal scope depends on the jurisdiction and current text; product features depend on release and settings.