# Semantic Kernel — Microsoft AI Agent Framework

> Semantic Kernel is Microsoft enterprise AI agent framework for Python, .NET, and Java. 27.6K+ GitHub stars. Multi-model, multi-agent, vector DB integration. MIT.

## Install

Save the content below to `.claude/skills/` or append to your `CLAUDE.md`:

## Quick Use

```bash
# Python
pip install semantic-kernel

# .NET
dotnet add package Microsoft.SemanticKernel

# Quick start (Python)
python -c "
from semantic_kernel import Kernel
from semantic_kernel.connectors.ai.open_ai import OpenAIChatCompletion
kernel = Kernel()
kernel.add_service(OpenAIChatCompletion(service_id='chat', ai_model_id='gpt-4o'))
print('Semantic Kernel ready!')
"
```

---

## Intro

Semantic Kernel is Microsoft's enterprise-ready AI agent orchestration framework for building intelligent agents and multi-agent systems. With 27,600+ GitHub stars and MIT license, it supports Python, .NET, and Java with multi-model LLM integration (OpenAI, Azure, HuggingFace, NVIDIA, Ollama), agent framework with tool/plugin access and planning, multi-agent orchestration, vector database integration (Azure AI Search, Elasticsearch, Chroma), multimodal processing (text, vision, audio), and business process modeling.

**Best for**: Enterprise teams building AI agents with Microsoft ecosystem integration
**Works with**: Claude Code, OpenAI Codex, Cursor, Gemini CLI, Windsurf
**Languages**: Python, .NET (C#), Java

---

## Key Features

- **Multi-language**: Python, .NET, Java SDKs
- **Multi-model**: OpenAI, Azure, HuggingFace, NVIDIA, Ollama, LMStudio
- **Agent framework**: Tools, plugins, and automatic planning
- **Multi-agent orchestration**: Complex workflow coordination
- **Vector DB integration**: Azure AI Search, Elasticsearch, Chroma
- **Multimodal**: Text, vision, audio processing
- **Enterprise-ready**: Observability, security, Azure integration

---

### FAQ

**Q: What is Semantic Kernel?**
A: Microsoft's AI agent framework with 27.6K+ stars. Python/.NET/Java, multi-model, multi-agent, vector DB, enterprise-ready. MIT licensed.

**Q: How do I install Semantic Kernel?**
A: Python: `pip install semantic-kernel`. .NET: `dotnet add package Microsoft.SemanticKernel`.

---

## Source & Thanks

> Created by [Microsoft](https://github.com/microsoft). Licensed under MIT.
> [microsoft/semantic-kernel](https://github.com/microsoft/semantic-kernel) — 27,600+ GitHub stars

---
Source: https://tokrepo.com/en/workflows/afa12811-f346-4e42-8dbe-10b87d1cb51a
Author: Skill Factory