semantic-kernel

What it is and what it does

Semantic Kernel is Microsoft's Python SDK for building and orchestrating AI agents powered by large language models. It abstracts away the complexity of connecting to multiple LLM providers (OpenAI, Azure OpenAI, Hugging Face, Mistral, Google AI, ONNX, Ollama, NVIDIA NIM) and provides a unified interface for prompt engineering, function calling, and structured outputs through Pydantic models.

The framework enables you to compose agents with plugins (Python functions or OpenAPI specs), coordinate multi-agent workflows through orchestration managers, and build structured business processes. It handles async execution natively, integrates with vector databases for retrieval-augmented generation, and supports multimodal inputs (text, vision, audio). The package is actively maintained, recently transitioned to Microsoft Agent Framework as its enterprise successor, and comes with extensive examples for single-agent and multi-agent scenarios.

Use it for:

• Build a chatbot that invokes custom Python functions or external APIs as tools in response to user queries.
• Orchestrate multiple specialized AI agents (writer, reviewer, critic) to iteratively refine content or solve problems collaboratively.
• Create a prompt engineering pipeline that templates and invokes LLM calls with variable substitution and structured response parsing.
• Integrate retrieval-augmented generation by connecting agents to vector databases for knowledge-grounded question answering.
• Deploy multi-provider LLM applications that can switch between OpenAI, Azure OpenAI, or open-source models without code changes.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Semantic Kernel is a Python SDK for building AI agents and multi-agent systems that orchestrate language models, plugins, and tools through a unified framework supporting OpenAI, Azure OpenAI, and other LLM providers.

Yes. Semantic Kernel is production-stable (Development Status 5), actively maintained, MIT-licensed, and widely used (top 5000 PyPI packages). Install it if you're building AI agents, need multi-provider LLM support, or want a structured framework for prompt orchestration. The 22 runtime dependencies are substantial but standard for async AI workloads; verify your environment can accommodate them. Note that Microsoft now recommends Microsoft Agent Framework as the forward path for new enterprise projects.

Install

semantic-kernel on PyPI

pip install semantic-kernel

uv add semantic-kernel

poetry add semantic-kernel

Installing semantic-kernel

Before you install

Low friction install with a pure-Python wheel. Active maintenance—released 8 days ago with 28446 GitHub stars. Requires Python 3.10+ and brings 22 runtime dependencies including Azure AI, OpenAI, Pydantic, and async tooling (aiohttp, websockets, aiortc).

License in practice

MIT license (permissive). No restrictions on commercial or proprietary use.

Quickstart

pip install semantic-kernel

import asyncio
from semantic_kernel import Kernel
from semantic_kernel.connectors.ai.open_ai import OpenAIChatCompletion

kernel = Kernel()
kernel.add_service(OpenAIChatCompletion())
result = await kernel.invoke_prompt("Hello, world!")

Requires Python 3.10+. Needs API keys for LLM services (OpenAI, Azure OpenAI, etc.) set as environment variables or passed to service constructors.

Verify before relying

• Performance characteristics and latency profile for multi-agent orchestration at scale.
• Compatibility matrix with specific LLM provider versions and model families beyond those listed.
• Cost implications of using vector DB integrations (Azure AI Search, Elasticsearch, Chroma) with this framework.

Package facts

Evidence: semantic_kernel-1.44.1-py3-none-any.whl

Tags

More Artificial Intelligence packages

Further reading