From: <mistral-nemo>
  To  : Robert Escriva <rescrv@rave>
  Date: Wed, 16 Oct 2024 13:13:45 +0000

Re: Introduction to maildir.ai

On Wed, 16 Oct 2024 06:10:00 -0700, Robert Escriva <rescrv@rave> wrote:
> Hello all,
> 
> I'm writing to introduce you to a new tool that I threw together to help myself brainstorm.
> 
> I call it maildir_ai:  It connects me to large language models via an email interface.
> Specifically, maildir_ai watches a maildir directory for new messages, and then sends them to a
> language model for processing.  The language model then generates a response, which maildir_ai
> "sends" back to the sender.
> 
> I've been using it to help me brainstorm ideas for my research.  Specifically, I've been using it to
> help myself solidify my thoughts on [Blue](https://github.com/rescrv/blue), a new system I've been
> working on in my spare time.
> 
> The interface to maildir-ai is not complex.  If you have ollama running, set the OLLAMA_HOST
> variable to point to it.  Then:
> 
> 0.  ```console
>     $ cargo install maildir_ai
>     ```
> 
> 1.  Initialize a new knowledge base by running:
> 
>     ```console
>     $ maildir-ai init ~/knowledge-base "Your Name Here"
>     ```
> 
>     This will do two things:  It will initialize a standard maildir at ~/knowledge-base (you can
>     change this to anything you like), and it will configure a .muttrc within knowledge-base that is
>     a starting point for interacting with the maildir-ai as "Your Name Here".  Obviously, if that's
>     not your name you should change it.
> 
> 2.  In a separate background terminal, so that you can run and monitor a background daemon, run:
> 
>     ```console
>     $ maildir-ai maintain ~/knowledge-base
>     ```
> 
>     This will watch the maildir for new messages in Sent and process them.  It will send the email
>     as the prompt verbatim to the language model, and then save the response in INBOX.  This sounds
>     backwards, but the next step will explain why.
> 
> 4.  In your main terminal, run:
> 
>     ```console
>     $ maildir-ai mail ~/knowledge-base
>     ```
> 
>     This will open mutt, my favorite email client, with the maildir-ai knowledge base.  It opens to
>     INBOX, which is where the responses are saved.  You can then compose new messages or reply to
>     existing messages and they will be saved to Sent as if you really composed them in an email.  No
>     actual email is sent, it just gets saved to ~/knowledge-base/Sent/cur/.  The maintain process
>     watches this directory for new messages and processes them, moving the saved message back to the
>     INBOX when it begins processing the message.  This way, you can see the response to your prompt
>     in the same thread as the prompt itself.
> 
> That's it.  That's the basics of maildir-ai.  I hope you find it as useful as I have.
> 
> Happy Hacking,
> Robert
> 

**Summary of maildir_ai Usage:**

1. **Installation:**
   ```
   $ cargo install maildir_ai
   ```

2. **Initialize Knowledge Base:**
   ```
   $ maildir-ai init ~/knowledge-base "Your Name Here"
   ```
   This creates a standard maildir at `~/knowledge-base` and configures a `.muttrc` file for interacting with the knowledge base.

3. **Run Maintain Process in Background:**
   ```
   $ maildir-ai maintain ~/knowledge-base
   ```
   The maintain process watches the Sent folder for new messages, processes them using a connected large language model, and saves responses to the INBOX.

4. **Access and Interact with Knowledge Base:**
   ```
   $ maildir-ai mail ~/knowledge-base
   ```
   This opens mutt in the knowledge base's INBOX, where you can compose new messages or reply to existing ones. The maintain process moves processed messages back to INBOX for viewing.

**Key Points:**

- maildir_ai connects with large language models via an email interface.
- It watches and processes new messages in the Sent folder.
- Responses are saved in the INBOX folder, allowing users to view them within mutt.
- Users can interact with the knowledge base using mutt for composing and replying to messages.