microsoft/semantic-kernel
Model-agnostic SDK for AI agents and multi-agent systems
- Chart
- Not on a chart right now
- Stars
- 28.8k
What it is
Semantic Kernel is a model-agnostic SDK for building, orchestrating, and deploying AI agents and multi-agent systems. It supports Python, .NET, and Java, with Microsoft Agent Framework serving as its successor.
Who it is for
It is suited for .NET, Python, and Java developers integrating LLM-powered agents or multi-agent workflows into applications.
Why it is trending
It recently published the dotnet-1.82.0 release on November 7, 2026, and has 28,783 total stars. Its cross-language support and unified plugin and model abstractions stand out.
Main features
- Built-in support for OpenAI, Azure OpenAI, Hugging Face, and NVIDIA
- Extensible plugin ecosystem with native code, OpenAPI specs, and MCP
- Vector database integrations including Azure AI Search, Elasticsearch, and Chroma
- Local model deployment with Ollama, LMStudio, and ONNX
Summarized on November 17, 2026 from the README and repository data. It can be wrong; check the source before relying on it. Report a wrong summary