Unpacking the Microsoft Agent Framework

"Earlier this year, Microsoft said it would bring its two different agent development platforms together, merging Semantic Kernel and AutoGen. It has now launched that merged platform as the Microsoft Agent Framework. At the time of the announcement, I noted that it made sense; Semantic Kernel was an in-production AI workflow engine that had evolved to support new agentic models, while AutoGen came from a research background and offered new ways to build multi-agent applications without writing code."

"Both tools were open source, so it's not surprising that Microsoft Agent Framework is too, developed in the open on GitHub, with sample code ready for experiments in your own systems or in a ready-to-try Codespace virtual development environment. This approach has allowed it to quickly adopt new agent development practices as they've become popular, adding support for Model Context Protocol (MCP), Agent2Agent, and more, as well as allowing you to choose your own AI models and providers."

"Workflow is still at the heart of the new framework. Building on the strengths of the Semantic Kernel and AutoGen agent implementations, the new framework offers support for workflow orchestration and agent orchestration. Workflow orchestration builds on Semantic Kernel and implements existing business processes and logic, calling a chain of agents as needed, constructing prompts using predefined formats, and populating values using results from earlier calls."

Microsoft merged Semantic Kernel and AutoGen into the Microsoft Agent Framework, released as open-source on GitHub with sample code and a Codespace environment. The framework supports workflow orchestration derived from Semantic Kernel for implementing business processes and logic via predefined prompt formats and chained agents. It also supports agent orchestration from AutoGen, using LLM-driven techniques to dynamically create agent chains from open-ended prompts. The platform has added support for Model Context Protocol (MCP) and Agent2Agent and allows selection of AI models and providers. Combining two distinct development paradigms creates integration and maintenance challenges.

Read at InfoWorld