Welcome to Microsoft's comprehensive multi-language framework for building, orchestrating, and deploying AI agents with support for both .NET and Python implementations. This framework provides everything from simple chat agents to complex multi-agent workflows with graph-based orchestration.
Watch the full Agent Framework introduction (30 min)
Python
pip install agent-framework --pre
# This will install all sub-packages, see `python/packages` for individual packages.
# It may take a minute on first install on Windows..NET
dotnet add package Microsoft.Agents.AI- Overview - High level overview of the framework
- Quick Start - Get started with a simple agent
- Tutorials - Step by step tutorials
- User Guide - In-depth user guide for building agents and workflows
- Migration from Semantic Kernel - Guide to migrate from Semantic Kernel
- Migration from AutoGen - Guide to migrate from AutoGen
Still have questions? Join our weekly office hours or ask questions in our Discord channel to get help from the team and other users.
- Graph-based Workflows: Connect agents and deterministic functions using data flows with streaming, checkpointing, human-in-the-loop, and time-travel capabilities
- AF Labs: Experimental packages for cutting-edge features including benchmarking, reinforcement learning, and research initiatives
- DevUI: Interactive developer UI for agent development, testing, and debugging workflows
See the DevUI in action (1 min)
- Python and C#/.NET Support: Full framework support for both Python and C#/.NET implementations with consistent APIs
- Observability: Built-in OpenTelemetry integration for distributed tracing, monitoring, and debugging
- Multiple Agent Provider Support: Support for various LLM providers with more being added continuously
- Middleware: Flexible middleware system for request/response processing, exception handling, and custom pipelines
- For bugs, please file a GitHub issue.
Create a simple Azure Responses Agent that writes a haiku about the Microsoft Agent Framework
# pip install agent-framework --pre
# Use `az login` to authenticate with Azure CLI
import os
import asyncio
from agent_framework.azure import AzureOpenAIResponsesClient
from azure.identity import AzureCliCredential
async def main():
# Initialize a chat agent with Azure OpenAI Responses
# the endpoint, deployment name, and api version can be set via environment variables
# or they can be passed in directly to the AzureOpenAIResponsesClient constructor
agent = AzureOpenAIResponsesClient(
# endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
# deployment_name=os.environ["AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME"],
# api_version=os.environ["AZURE_OPENAI_API_VERSION"],
# api_key=os.environ["AZURE_OPENAI_API_KEY"], # Optional if using AzureCliCredential
credential=AzureCliCredential(), # Optional, if using api_key
).as_agent(
name="HaikuBot",
instructions="You are an upbeat assistant that writes beautifully.",
)
print(await agent.run("Write a haiku about Microsoft Agent Framework."))
if __name__ == "__main__":
asyncio.run(main())Create a simple Agent, using OpenAI Responses, that writes a haiku about the Microsoft Agent Framework
// dotnet add package Microsoft.Agents.AI.OpenAI --prerelease
using Microsoft.Agents.AI;
using OpenAI;
using OpenAI.Responses;
// Replace the <apikey> with your OpenAI API key.
var agent = new OpenAIClient("<apikey>")
.GetResponsesClient("gpt-4o-mini")
.AsAIAgent(name: "HaikuBot", instructions: "You are an upbeat assistant that writes beautifully.");
Console.WriteLine(await agent.RunAsync("Write a haiku about Microsoft Agent Framework."));Create a simple Agent, using Microsoft Foundry with token-based auth, that writes a haiku about the Microsoft Agent Framework
// dotnet add package Microsoft.Agents.AI.AzureAI --prerelease
// dotnet add package Azure.Identity
// Use `az login` to authenticate with Azure CLI
using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
var endpoint = Environment.GetEnvironmentVariable("AZURE_AI_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("AZURE_AI_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("AZURE_AI_MODEL_DEPLOYMENT_NAME") ?? "gpt-4o-mini";
var agent = new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential())
.AsAIAgent(model: deploymentName, name: "HaikuBot", instructions: "You are an upbeat assistant that writes beautifully.");
Console.WriteLine(await agent.RunAsync("Write a haiku about Microsoft Agent Framework."));- Getting Started: progressive tutorial from hello-world to hosting
- Agent Concepts: deep-dive samples by topic (tools, middleware, providers, etc.)
- Workflows: workflow creation and integration with agents
- Hosting: A2A, Azure Functions, Durable Task hosting
- End-to-End: full applications, evaluation, and demos
- Getting Started: progressive tutorial from hello agent to hosting
- Agent Concepts: basic agent creation and tool usage
- Agent Providers: samples showing different agent providers
- Workflows: advanced multi-agent patterns and workflow orchestration
- Hosting: A2A, Durable Agents, Durable Workflows
- End-to-End: full applications and demos
| Problem | Cause | Fix |
|---|---|---|
| Authentication errors when using Azure credentials | Not signed in to Azure CLI | Run az login before starting your app |
| API key errors | Wrong or missing API key | Verify the key and ensure it's for the correct resource/provider |
Tip:
DefaultAzureCredentialis convenient for development but in production, consider using a specific credential (e.g.,ManagedIdentityCredential) to avoid latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
The samples typically read configuration from environment variables. Common required variables:
| Variable | Used by | Purpose |
|---|---|---|
AZURE_OPENAI_ENDPOINT |
Azure OpenAI samples | Your Azure OpenAI resource URL |
AZURE_OPENAI_DEPLOYMENT_NAME |
Azure OpenAI samples | Model deployment name (e.g. gpt-4o-mini) |
AZURE_AI_PROJECT_ENDPOINT |
Microsoft Foundry samples | Your Microsoft Foundry project endpoint |
AZURE_AI_MODEL_DEPLOYMENT_NAME |
Microsoft Foundry samples | Model deployment name |
OPENAI_API_KEY |
OpenAI (non-Azure) samples | Your OpenAI platform API key |
If you use the Microsoft Agent Framework to build applications that operate with third-party servers or agents, you do so at your own risk. We recommend reviewing all data being shared with third-party servers or agents and being cognizant of third-party practices for retention and location of data. It is your responsibility to manage whether your data will flow outside of your organization's Azure compliance and geographic boundaries and any related implications.