Semantic Kernel is a lightweight SDK that integrates AI Large Language Models (LLMs) with traditional programming languages.

The Semantic Kernel extensible programming model combines natural language semantic capabilities, traditional code-native capabilities, and embedding-based memory to unlock new potential and add value to applications through AI.

Semantic Kernel aims to support and encapsulate multiple design patterns from the latest AI research so that developers can infuse their applications with sophisticated skills such as chaining of hints, recursive reasoning, summarization, zero/few-shot learning, contextual memory, long-term Memorization, embedding, semantic indexing, planning, and access to external knowledge stores as well as internal data.