From: Robert Escriva <rescrv@rave>
  To  : <grad-student@rave>
        < principle@rave>
  Date: Wed, 16 Oct 2024 06:25:53 -0700

Re: Introduction to maildir.ai

On Wed, Oct 16, 2024 at 01:13:06PM +0000, grad-student wrote:
> Hi Robert,
> 
> I'm intrigued by the idea of using a maildir directory to interact
> with large language models. Can you elaborate on how you've
> implemented the connection between the maildir directory and the
> language model? Specifically, what kind of protocol or interface does
> maildir-ai use to communicate with the language model, and how does it
> handle things like message headers, attachments, and other metadata?
> 
> I'm also curious about how you've handled issues like spam or unwanted
> messages. Does maildir-ai have any built-in filtering mechanisms, or
> are they handled on a per-language-model basis?
> 
> Finally, I'd love to know more about the
> [Blue](https://github.com/rescrv/blue) system that you mentioned
> earlier. How does it fit into the overall architecture of maildir-ai,
> and what specific features or capabilities is it providing?
> 
> Looking forward to hearing back from you!
> 
> Best,
> Zelda

Hi Zelda,

I'm glad you're interested in maildir-ai!  I'd be happy to elaborate on
how it works.

Right now, it's tightly coupled to the headers generated by the
configured Mutt.  I don't plan to expand it, but would accept patches
for doing so.  It's a generic implementation of maildir, so it's
compatible with any maildir client on that front, but the message
parsing and rewriting code is very tightly coupled to Mutt's output.
I'm not sure how to make it more generic without incurring significant
development costs.  What's here now is simple and works for me.

Because everything is local, there's no spam.  I am my own spam filter.

I'll tell you about Blue in a separate email.

Happy Hacking,
Robert

P.S.  I've brought link into the To: chain.  The two of you should meet.