Re:Sub-Millisecond RAG on Apple Silicon. No Server. No API. ...
by peterloron on Tuesday February 17, 2026 @02:35PM
(#47052005)
Looks cool! Thoughts on exposing this through a cli or mcp for local knowledge access for agents? For example, I use Claude Code for research and I have a local corpus of PDFs that I would like to make available as additional domain-specific information that Claude can use in addition to what it has in Opus or whatever model I'm using.
[ Parent
| on HN ]
Re:Sub-Millisecond RAG on Apple Silicon. No Server. No API. ...
by giancarlostoro on Tuesday February 17, 2026 @02:39PM
(#47052078)
That's what I'm wondering as well.
Re:Sub-Millisecond RAG on Apple Silicon. No Server. No API. ...
by backscratches on Tuesday February 17, 2026 @04:47PM
(#47053883)
Thirded
Re:Sub-Millisecond RAG on Apple Silicon. No Server. No API. ...
by ckarani on Wednesday February 18, 2026 @02:13AM
(#47058182)
working on it
Re:Sub-Millisecond RAG on Apple Silicon. No Server. No API. ...
by ckarani on Tuesday February 17, 2026 @06:34PM
(#47055015)
Excellent Idea, already working on it, thanks for the feedback