microsoft/agent-framework
A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.
What it solves
Microsoft Agent Framework (MAF) 提供一致且具生产级的基础，帮助构建和运营 AI 代理及多代理工作流。它弥合了简单原型与生产系统之间的差距，提供在基本聊天循环中常缺失的编排、耐久性和可观测性工具。
How it works
MAF 是一个支持 Python 和 .NET 的多语言框架。它允许开发者使用图形化模式（如顺序、并行和组协作）来定义代理并进行编排，以处理复杂任务。框架支持多种 LLM 提供商（包括 Azure OpenAI 和 OpenAI），并包含用于自定义请求/响应处理的中间件系统。它还提供通过 YAML 的声明式代理定义以及专用的 DevUI 用于测试和调试。
Who it’s for
它面向需要超越无状态聊天循环、构建耐久、可观测且受治理的代理系统，并可部署到本地或云环境的开发团队。
Highlights
- Multi-language support: Consistent APIs across Python and C#/.NET.
- Graph-based orchestration: Supports complex workflows including handoffs, concurrent execution, and human-in-the-loop control.
- Production readiness: Built-in OpenTelemetry integration for monitoring and features like checkpointing and time-travel.
- Flexible deployment: Supports various hosting patterns, including Foundry-hosted agents, Azure Functions, and Durable Task hosting.
- Extensible architecture: Includes a middleware system and support for multiple LLM providers to prevent vendor lock-in.