$ show microsoft/Agents
This repository contains the Microsoft 365 Agents SDK and samples for building conversational agents deployable to Microsoft 365 channels (Teams, Copilot Studio, web chat) and custom channels. The SDK is AI-service agnostic, allowing integration of any AI model or service. Samples demonstrate common agent patterns including welcome messages, tool usage (dice roller, inventory, weather lookup), streaming responses, authentication (OBO, auto sign-in), observability (OpenTelemetry), and integrations (Genesys, Slack, Semantic Kernel, LangChain). The architecture follows a consistent pattern across languages: initialize storage, connection manager, adapter, and authorization; instantiate AgentApplication; register event handlers; start server. Entry points vary by language (Program.cs for .NET, src/index.ts for Node.js, src/main.py for Python). External dependencies include Microsoft Graph, GitHub API, Azure OpenAI, and various agent frameworks.
The LLM identified 3 files worth highlighting for reuse:
Provides extension methods to add OpenTelemetry tracing, metrics, and logging to .NET agents. Configures Azure Monitor exporter and automatic instrumentation for HTTP requests. Self-contained, depends only on OpenTelemetry packages, and can be reused in any .NET agent project with minimal configuration changes.
Encapsulates Microsoft Graph API calls to fetch user information and profile photos with caching to reduce API calls. Handles errors and is independent of agent logic. Can be extracted and used in any Node.js agent requiring Microsoft Graph integration.
Sets up OpenTelemetry tracing for Python agents, configuring Azure Monitor exporter and enabling instrumentation for common libraries. Self-contained function that can be imported and called in any Python agent's startup to add observability with minimal changes.