zsh_codex

I've been using https://github.com/tom-doerr/zsh_codex with gpt4-o and it saves a lot of strokes as compared to github copilot cli to query, since I just have to press ctrl-x in addition to the prompt. Magic-cli also seems to be using same workflow as github copilot, so I'm not rushing to use it.

All of the alternatives commented so far have the same downside, you got a LLM response and you can either run it or abort. https://github.com/tom-doerr/zsh_codex ^ This is much nicer as it hook into zsh completion so you got a response that drop right into the shell input (enter to execute or edit away) Also you can write shell script directly in prompt and use it to auto complete the rest

> It should tell you the commands first rather than just executing them. From the videos, I believe you have to press Enter to actually execute the suggested command. > why the example video only shows PowerShell too The readme did say that it was inspired by a similar project targetting zsh[0], so I don't see why over time the model couldn't improve to suggest what you want. [0]: https://github.com/tom-doerr/zsh_codex

This shell plugin I wrote turns out to be really good at writing git commands. The git commands below are AI generated from the comments. ``` printcon-ml git:(master) # show the date the file fastai_main.py was first added to the repo git log --diff-filter=A --follow --format="%ad" --date=short -- fastai_main.py printcon-ml git:(master) # show the commit before the 2021-12-04 git log --before=2021-12-04 printcon-ml git:(develop) # show all git branches and their creation dates git for-each-ref --sort=-committerdate --format='%(refname:short), %(committerdate:short)' refs/heads/ develop, 2022-04-28 multiprocessing_manager, 2022-04-28 master, 2022-01-11 plotting_upgrade, 2022-01-04 image_samples, 2022-01-03 label_output, 2021-10-12 percentages_output, 2021-08-10 add_model_argument, 2021-08-10 model_9, 2021-08-05 model_7, 2021-08-05