Microsoft Launches Agent Framework 1.0 With Multi-Agent Orchestration Support for .NET and Python
Summary
Microsoft officially launches Agent Framework 1.0 for .NET and Python, delivering production-ready multi-agent orchestration with support for Azure OpenAI, Anthropic Claude, Google Gemini, Amazon Bedrock, and Ollama, plus enterprise features like declarative YAML workflows, agent memory, and cross-runtime interoperability via MCP and A2A protocols.
Key Points
- Microsoft Agent Framework version 1.0 is now officially released for both .NET and Python, marking a production-ready milestone with stable APIs, long-term support, and enterprise-grade multi-agent orchestration built on the foundations of Semantic Kernel and AutoGen.
- Version 1.0 ships with a robust feature set including multi-provider model support for Azure OpenAI, Anthropic Claude, Amazon Bedrock, Google Gemini, and Ollama, alongside agent memory, middleware hooks, declarative YAML-based workflows, and cross-runtime interoperability via MCP and A2A protocols.
- Preview features are also launching alongside the stable release, including a browser-based DevUI debugger, Foundry Hosted Agent integration, GitHub Copilot and Claude Code SDK support, and frontend adapters for CopilotKit and ChatKit, with migration guides available for teams coming from Semantic Kernel or AutoGen.