Semantic Kernel
Enterprise SDK for adding AI agents and plugins to existing applications
View on GitHubWhat it solves
Adding AI capabilities to an existing enterprise application without rebuilding it: Semantic Kernel slots into your DI container and treats LLMs as another service.
Overview
Microsoft's production-grade SDK for integrating LLMs into enterprise applications across Python, C#, and Java. The core abstraction is the Kernel, a dependency injection container that registers AI services, plugins (functions the model can call), and memory connectors. Planners let the model decide at runtime which plugins to invoke and in what order.
Key facts
- Language
- C#
- License
- MIT
- Maturity
- Stable
- Maintainer
- microsoft
- Reviewed
- 2026-06-11
Where to start
The getting started notebooks walk the Kernel → Plugin → Planner hierarchy in the order you'll actually need it.
python/samples/getting_started/01-basic-loading-the-kernel.ipynbTechnologies
More in this domain
LangGraph
Stateful multi-agent orchestration for LLM applications
The state management problem in multi-agent systems: how you build agents that pass context across turns without losing the execution thread.
AutoGen
Multi-agent conversation framework from Microsoft Research
How to coordinate multiple specialized agents toward a shared goal without writing low-level orchestration logic by hand.
CrewAI
Role-based multi-agent orchestration for collaborative task execution
The boilerplate problem in multi-agent setup: defining roles, delegation rules, and task routing without writing a custom orchestration graph.