Semantic Kernel (SK) is a lightweight SDK from Microsoft aimed at enabling integration of AI Large Language Models with conventional programming languages. 

According to the project’s GitHub page, the SK extensible programming model brings together natural language semantic functions, traditional code native functions, and embeddings-based memory in order to access new potential and add value to apps with AI.

SK was designed to support and include design patterns from recent AI research, allowing developers to enrich their applications with complicated skills such as prompt chaining, recursive reasoning, and summarization.

Furthermore, users can infuse their apps with zero/few-shot learning, contextual memory, long-term memory, embeddings, semantic indexing, planning, and accessing external knowledge stores as well as the users own data.   

“By joining the SK community, you can build AI-first apps faster and have a front-row peek at how the SDK is being built. SK has been released as open-source so that more pioneering developers can join us in crafting the future of this landmark moment in the history of computing,” the project maintainers wrote on SK’s GitHub page.

Additionally, SK supports prompt templating, function chaining, vectorized memory, and intelligent planning capabilities out of the box.

More information is available in the documentation.