Hi all! I'm new to the community but wanted to show off a project I'm proud of. This is called Natta Toolkit, and it was meant to be a control center/routing method for tools I use at work and personally. I made it open source, because I really wanted anyone to be able to stress test it and give feedback.
The goal I was going for was to have a single route to local scripts that otherwise needed aliases, direct calls etc while I was working. Instead, I created a non-AI required way of calling them. I did want natural language to be usable as well, so that's where leveraging AI came from. I tried a local decision model called OpenJev first, and unfortunately it did not produce great results, so I decided to make use of ChatGPT CLI, specifically Luna as it was cheap and more than powerful enough when using the setup I created to route.
I only recently began to work with AI, so please give me any feedback. I am aware this is a very defensive implementation of it and that is by design, but I would still love feedback!
The goal I was going for was to have a single route to local scripts that otherwise needed aliases, direct calls etc while I was working. Instead, I created a non-AI required way of calling them. I did want natural language to be usable as well, so that's where leveraging AI came from. I tried a local decision model called OpenJev first, and unfortunately it did not produce great results, so I decided to make use of ChatGPT CLI, specifically Luna as it was cheap and more than powerful enough when using the setup I created to route.
I only recently began to work with AI, so please give me any feedback. I am aware this is a very defensive implementation of it and that is by design, but I would still love feedback!