Semantic Kernel
Microsoft's open-source SDK for integrating large language models into applications, with support for plugins, memory, and planning.
- Actively maintained
- Well documented
- Permissive license
Overview
Semantic Kernel lets developers combine LLM prompts with native code functions as interchangeable "plugins," giving an LLM the ability to call real application logic, and provides memory and planning abstractions for building more autonomous, multi-step AI features. It's designed to integrate naturally into existing .NET, Python, or Java codebases rather than requiring a rewrite.
Semantic Kernel is a fit for teams already working in the Microsoft ecosystem (.NET in particular) who want an LLM orchestration SDK that feels native to that environment, an alternative to LangChain (also in this catalog) with first-class multi-language support including strong .NET integration.
Why it's in this catalog
Catalog rating: ★★★☆☆ (3/5)
Microsoft's LLM orchestration SDK, meaningful overlap with LangChain but distinct enterprise/.NET positioning.
- Mature
- Vendor-backed
- Categories
- AI & Machine Learning
- Languages
- C#, Python
- License
- MIT
Related Projects
Pydantic AI
MITType-safe agent framework from the team behind Pydantic, bringing familiar Python typing and validation patterns to LLM application development.
Actively maintained
- AI & Machine Learning
LlamaIndex
MITData framework for connecting large language models to your own data - documents, databases, APIs - for retrieval-augmented applications.
Actively maintained
- AI & Machine Learning
Haystack
Apache-2.0Open-source framework for building production-ready search and RAG (retrieval-augmented generation) applications with LLMs.
Actively maintained
- AI & Machine Learning
Instructor
MITLibrary for getting reliable, structured data output from LLMs using function-calling APIs and Pydantic models for validation.
Actively maintained
- AI & Machine Learning
Spotted an error? Suggest an edit on GitHub.