dabit3

See more of my writing here.

In this post, I'll start from scratch and build up to OpenClaw's architecture step by step, showing how you could have invented it yourself from first principles, using nothing but a messaging API, an LLM, and the desire to make AI actually useful outside the chat window.

End goal: understand how persistent AI assistants work, so you can build your own (or become an OpenClaw power user).

First, let's establish the problem

When you use ChatGPT or Claude in a browser, there are several limitations:

meghbhalerao

import SimpleITK as sitk

# read image
inputImage = sitk.ReadImage('/path/to/input.nii.gz')

# get result in the form of a numpy array
npa_res = my_algorithm(sitk.GetArrayFromImage(inputImage)) # my_algorithm does something fancy

# Converting back to SimpleITK (assumes we didn't move the image in space as we copy the information from the original)
result_image = sitk.GetImageFromArray(npa_res)