Why does Cascaide exist?

Note: This will be the only verbose part of this documentation. Bear with me.

AI orchestration is is somewhat of a new domain. It’s the wild west out here.

Large Language Models (LLMs) burst into the scene towards the end of 2022 with the release of ChatGPT. Since then things have moved fast, so fast that we consider papers than came out in 2023 ancient. There has been so much attention, talent and money has flowed copiously into AI, very much like the early days of the dot com rush. Soon, we realised that robust software frameworks are required to actually put these smart models to work, birthing the first of the AI orchestration frameworks. Everyone started building AI agents. So did I.

While this is all well and good, this downpour also resulted in hype. Copious amounts of it. And with hype came the idea that orchestration is supposed to be an extremely complex endeavour requiring frameworks that have massive codebases and impenetrable abstractions.

This is my claim

• AI orchestration frameworks can and should be lightweight
• The abstractions should be light enough to quickly grasp and powerful enough to allow you to build whatever you need.

Cascaide is my shot at this goal. Do help, maybe we can build something good.