Microsoft has launched the Microsoft Agent Framework, an open-source SDK and runtime for constructing, orchestrating, and deploying AI brokers and multi-agent workflows, with full framework help for .NET and Python.
Launched October 1 and accessible on GitHub, the Agent Framework is designed to let builders construct every little thing from easy chat brokers to complicated multi-agent workflows with graph-based orchestration, Microsoft mentioned. Builders can experiment regionally with the framework after which deploy to the Azure AI Foundry for AI apps, with observability, sturdiness, and compliance built-in. Multi-agent techniques may be constructed connecting Azure AI Foundry, Microsoft 365 Copilot, and different agent platforms.
[ Related: Agentic AI – Ongoing news and insights ]
Microsoft mentioned that the Microsoft Agent Framework brings collectively and extends the concepts from the Semantic Kernel and AutoGen initiatives, and that builders at the moment utilizing these initiatives will discover the transition to the Agent Framework easy. The Agent Framework helps the Mannequin Context Protocol (MCP) and the Agent2Agent (A2A) protocol and options an OpenAPI-first design and cloud-agnostic runtime. In consequence, the Agent Framework allows the next capabilities, in keeping with Microsoft:
