The concept of wrapping your CLIs to make them more token-efficient [video]
youtube.comDoes RTK actually lead to savings? I recall seeing some opinions suggesting that you save on tokens because the outputs are shorter, but the quality ends up suffering—and sometimes token efficiency doesn't even improve, because the model doesn't fully grasp the output returned by RTK. Though, I must admit that I haven't personally benchmarked this myself.
Hey, RTK saves between 2% and 7% on costs, it highly depends of your usage, to get more savings use a specific pipeline (which can reach 20% costs savings) : https://www.rtk-ai.app/pipelines/
By default what run is the bash compression pipeline, which is what RTK has been known for, but you can go further with others pipeline with smart routing for example.
You can build your own as well
Here’s an example of gh-axi, which wraps the GitHub CLI and prepares the most relevant information for agents—so the LLM doesn’t have to filter it out itself. So simple! I haven’t yet formed an opinion on whether this is overengineering or a genuine way to save time and money; I also haven’t looked into how it compares to the cost savings provided by RTK.
Good point—though, tbh I’ve never benchmarked this myself. I just looked at the RTK gain, and it seemed to do the job." That said, because of my specific sandbox configuration, I’ve added gh and git to my "excluded tools" list, so I’m in no position to compare it against gh-axi.