Semantic Kernel
by Microsoft
Microsoft's enterprise-flavoured framework for AI agents. .NET-first, with Python and Java siblings.
OSS
Semantic Kernel
Added 17 May 2026
Overview
Semantic Kernel is Microsoft's open-source framework for building AI agents and chaining LLM calls in enterprise apps. Strongest in the .NET ecosystem (with Python and Java SDKs alongside), and a clear fit for teams already running on Azure OpenAI.
Best for
Best for
.NET and enterprise teams adopting AI agents
Use cases
- Build production agents in a .NET enterprise app
- Bridge LLMs into existing line-of-business systems
- Use Azure OpenAI with first-class framework support
- Build cross-language agents across .NET, Python, and Java
Notes
Why it matters
The .NET enterprise world is large and underserved by the Python-heavy AI ecosystem. Semantic Kernel is the obvious choice when the rest of the stack is .NET.
How teams use it in production
Start in the host stack you already run. Use Semantic Kernel to glue LLM calls into existing enterprise services. Adopt patterns from the LangChain or LlamaIndex world only when they map cleanly.
What to watch
Microsoft’s strategy across Semantic Kernel and AutoGen is converging. Watch how the two products settle into a single recommended path.
Pros
- .NET first-class, rare in the agent ecosystem
- Strong fit with Azure OpenAI
- Python and Java SDKs for cross-stack teams
- Microsoft enterprise backing
Cons
- Less momentum than LangChain or LlamaIndex on the Python side
- Smaller agent-pattern community
- Best in Azure-aligned shops, less natural elsewhere
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.