Early-stage Hackable HCI tools

An AI-first, privacy respecting, integrated diagnostic and development suite built the Unix way, through small tools that can be orchestrated together.

• Tmux Talkers: Rebranded as sidechat
• Shell Snoopers: Tiny tools for shining up your shell
• Xorg Xtractors: LLM interception and injection in your Xorg

The Shell Snoopers

shell-hook, shellwrap and wtf

Shell-hook.zsh

Moved to Zummoner.

Shellwrap

Moved to ESChatch.

Tabchat

This is a fairly simple script you can just add to your .{shell}sh:

function tabchat() {
    bt html $(bt active | cut -d ' ' -f 1) | markitdown | llm "Here is a document I'm going to ask you about" | sd
    llm chat -c | sd
}

This uses brotab to get the html from the active tab (bt html) and then uses markitdown to convert it into ingestable markdown for an llm, then it uses simonw's llm to add it to a context window and streamdown to format the markdowne.

WTF

A tool designed to read a directory of files, describe their content, categorize their purposes and answer basic questions. Example!

(Notice how it has no idea what shellwrap does. Told you it was new! ;-) )

The Xorg Xtractors

kb-capture.py and llm-magic

kb-capture.py captures keyboard events from an X server and converts them into a string. It exits and prints the captured string when a semicolon (;) or colon (:) is pressed. llm-magic is a shell script that uses kb-capture.py to capture keyboard input, sends it to an LLM for processing, and displays the LLM's response using dzen2 and then types it out using xdotool.

Their powers combined gives you llm prompting in any application. Here the user is

• ssh'ing to a remote machine
• using a classic text editor (scite)
• using classic vim

I do a keystroke to invoke llm-magic, type my request, then ; and it replaces my query with the response. Totally magic. Just like it says.

Thanks for stopping by!