HumlaGlossary
What is RAG (retrieval-augmented generation)?
RAG (retrieval-augmented generation) is a technique where an AI first retrieves relevant documents, then writes its answer grounded in what it found — ideally citing the sources it used.
- Free, no account
- Open source, MIT
- Apple Silicon, macOS 13 or later
In depth
What it means
It beats pasting a whole transcript into a chatbot: the model pulls in only the passages that matter and can point back to where each fact came from, so answers stay grounded instead of guessed.
Humla runs the whole RAG loop locally on your Mac, over your own meeting notes — retrieval, reading, and an answer with citation chips — with nothing sent to a server unless you pick a cloud model.
Related
Where this comes up
Keep your meetings on your Mac.
Free and open source. Apple Silicon, macOS 13 or later.