Writing

zsh + llm config

LLMs to suggest commands for zsh. No external dependencies. Fully local.

Noel Thomas

Founder

1 min read

  • written by human
  • technical

GitHub

This config allows for command completion if an LLM is turned on.

#Usage

  1. Save your current config if needed.

  2. Move .zshrc, .functions, and .llm-functions to the appropriate directory. Typically, this is the root directory.

  3. Start a new terminal, or run source <path>/.zshrc (typically source ~/.zshrc) on a running terminal.

  4. To enable LLM features, run a llamafile server. See llamafile for more information.

#Features

Click below to see the features video.

See the features video

Here's a list of some other functions included in .function.

Function NameDescription
checksitecheck if a website is up
portpidfind process name and PID by port
genpassgenerate a random password
dockercleanremove all stopped containers
dockerimagecleanremove all dangling images
dockerkillallstop and remove all containers
lsflist all functions and descriptions defined in ~/.functions
upgo up multiple directories
gogitgo to the GitHub dir
gsgit status shortcut
gpgit pull shortcut
gacpgit add, commit, and push
mkvenvcreate venv with python 3.11
mkcdmake directory and switch in
alpinedstart fsh in an alpine container

More articles

Code that runs in the post

A fenced block tagged artifact stops being a listing and starts being a program — including a transformer that runs entirely in your browser.

Read more

Transformers

The architecture that changed the world.

Read more

Address

Calgary, AB · Montreal, QC

Calgary
+1 (587) 700-9968
Montreal
+1 (825) 365-9891
Hours
09:00 – 17:00 · MT