Microsoft's open-source AI SDK that connects LLMs, plugins, memory, and planners into production-grade .NET and Python agents.
Five passes over the same idea, each from a different angle. Do them in order, or jump to whichever you need.
Semantic Kernel gives you a structured abstraction layer over LLM chaos. Plugins wrap your business logic so any AI model can call it. Memory stores give agents persistence. Planners decompose goals into sequences of plugin calls. The result is a production-tested framework that runs in .NET, Python, and Java with the reliability enterprise teams expect.
Where this topic shows up outside its home domain:
