wrapyfi VS evarobot

The authors present an example of combining Wrapyfi (https://github.com/fabawi/wrapyfi), a Python wrapper for message-oriented and robotics middleware, with LLaMA (https://github.com/facebookresearch/llama), a series of large language models from Meta AI. They demonstrate how Wrapyfi can enable running LLaMA on multiple mid-range machines with high inference speed and low cost. They also provide links to their GitHub repository (https://github.com/modular-ml/wrapyfi-examples_llama) and paper (https://arxiv.org/abs/2302.09648) for more details. They state that this example can revolutionize natural language processing tasks such as text generation, summarization, question answering, sentiment analysis, etc. without having to buy new hardware and use their existing infrastructure!

I am sorry if the question sounds a little aggressive but I want it to be direct. I was just messing around with ROS and was comparing Neuronbot (Noetic) and Evarobot. I have tried both and Neuronbot is better for dynamic environment (and faster as well). I compared their file structures and some navigation files, and found the only difference to be the larger range of planners Neuronbot was using. There were no custom nodes or services publishing goals, optimizing paths, global planner, etc., in either of them.

Now I want to do the fun stuff and actually write my own code for a robot. I found evabot which seems to be perfect (it's just a simulation with a 2d navigation tool that doesn't work for dynamic environments). I know a little bit of C++ but prefer developing on Python (hopefully 100% Python). My goal is to make 2d navigation work in a dynamic environment.