I'd consider using something besides 'list all files' as first example in the gif. I'd think anyone who opens a terminal knows how to do that so listing files in a directory and hitting a spinner isn't very inspiring.<p>The second curl example is better since plenty of people won't know that off the top of their head.
A reminder to users of Github CoPilot who may be unaware, there is also a terminal version you can install included in your subscription. It's ok. (Edit) There is a waitlist.<p><a href="https://githubnext.com/projects/copilot-cli" rel="nofollow noreferrer">https://githubnext.com/projects/copilot-cli</a>
All of the alternatives commented so far have the same downside, you got a LLM response and you can either run it or abort.<p><a href="https://github.com/tom-doerr/zsh_codex">https://github.com/tom-doerr/zsh_codex</a><p>^ 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)<p>Also you can write shell script directly in prompt and use it to auto complete the rest
I've built a similar shell script a while ago and still use it quite frequently: <a href="https://github.com/Luanf/cligpt">https://github.com/Luanf/cligpt</a>
There's also <a href="https://www.warp.dev" rel="nofollow noreferrer">https://www.warp.dev</a><p>I've been using it for the past few weeks and it's really sleek. I actually don't use the AI features very often because I'm fluent in the terminal, but it's nice to know it's there if I need it.<p>Some people get weirded out by the fact that it's VC funded and they collect telemetry, but I think you can turn that off.
I was surprised that Whiz could use tools like ffmpeg even though it tells ChatGPT to only use available shell commands. I asked it to "convert demo.mov to an mp4" and "cut the first five seconds of demo.mp4" and it came back with the correct commands. I guess that was enough to allow it to assume ffmpeg is probably installed. Pretty cool!
Seems like a perfect use case for local models. Not sure I want to be sending my .bash_profile or .bash_history (or local env vars...) to OpenAI. And I can't imagine doing anything in the terminal that llama2-code-7b couldn't make sense of. That can trivially run on an M1 with 8GB.
What are the security implications of this?<p>If you ask it something like “pipe the output of <CLI> using <MY_SECRET_TOKEN> to grep to find XYZ”
It is quite similar to <a href="https://github.com/KillianLucas/open-interpreter">https://github.com/KillianLucas/open-interpreter</a><p>Such terminal tools are quite like AI agents, it should think about steps and then execute one by one.
For people who use terminal a lot, I find shell gpt a good mixture [1]. Flexible enough to pipe commands, generic enough to ask questions.<p>[1] <a href="https://github.com/TheR1D/shell_gpt">https://github.com/TheR1D/shell_gpt</a>
How does it compare to gorilla cli? <a href="https://github.com/gorilla-llm/gorilla-cli">https://github.com/gorilla-llm/gorilla-cli</a>
I tried this but when I am running commands like wz can you install beautifulsoup and such things then it is giving me the syntex error: JSON<p>command is: "wz can you install bs4"