News
Semantic Kernel Agent Framework Graduates to Release Candidate
With agentic AI now firmly established as a key component of modern software development, Microsoft graduated its Semantic Kernel Agent Framework to Release Candidate 1 status.
That was announced last week along with the release of Semantic Kernel 1.40 (.NET) and 1.22.0 (Python).
[Click on image for larger view.] Semantic Kernel (source: Microsoft).
Designed to streamline the development of AI agents for enterprise applications, the Semantic Kernel Agent Framework serves as an extensible and interoperable framework that enables developers to build, orchestrate, and deploy AI-driven agents with various capabilities. It was announced as an experimental project last August (see "Semantic Kernel AI SDK Gets Autonomous Agents (Experimental)").
It builds on functionality such as retrieval augmentation generation (RAG) in the pursuit of fully autonomous agents that can respond to human prompts with minimal human intervention, even interacting with one another to fulfill assigned tasks.
[Click on image for larger view.] Multiple Agents Interacting (source: Microsoft).
"This marks a significant milestone in our journey toward providing a robust, versatile framework for building AI agents for enterprise applications," said Shawn Henry in a post that goes on to demonstrate the code needed to create a Chat Agent with tool plugins.
Plugins and integrations are key to offering, which is not tied to a single AI provider, but rather works with a range of AI services, with Henry highlighting preview functionality for expanded agent provider capabilities, noting Semantic Kernel now supports agents from:
- Azure AI Agent Service
- OpenAI Assistants
- AWS Bedrock
- Crew AI
- AutoGen
Those all work with the C# and Python implementations, except for AutoGen, which nows supports only Python, though the team is now focusing on integration with AutoGen.
Developed by Microsoft Research, AutoGen is an open-source framework designed to simplify the creation and management of multi-agent AI systems. It provides tools for defining AI agents that can collaborate, communicate, and perform complex tasks through structured workflows. It's particularly useful for building intelligent agents that leverage large language models (LLMs) like OpenAI’s GPT-4, Azure OpenAI models, and other AI services. For more on that, see the article, "Researchers Take AI Agents to the Next Level with the AutoGen Framework.
About the Author
David Ramel is an editor and writer at Converge 360.