azure-ai-agents

What it is and what it does

Azure AI Agents is a Python client library for building and managing AI agents on Microsoft's Azure AI Agents Service. It provides synchronous and asynchronous APIs to create agents, manage threads and messages, and orchestrate agent runs with support for multiple LLM providers and a rich tool ecosystem (file search, code interpretation, function calling, Bing grounding, Azure AI Search, OpenAPI integration). The library handles authentication via Azure Entra ID and integrates with Azure AI Foundry projects for resource management.

The package is designed for developers building generative AI applications that need agentic capabilities—agents that can reason, use tools, and interact with external systems. It abstracts away the complexity of the underlying Azure AI Agents Service, offering both synchronous and asynchronous clients. While it can be used independently, the documentation recommends pairing it with azure-ai-projects for simplified access to advanced features like agent lifecycle management, model enumeration, and observability.

Use it for:

• Build a customer support agent that searches internal documentation and executes code to troubleshoot issues.
• Create a data analysis agent that interprets code, processes files, and retrieves information from Azure AI Search.
• Develop a multi-turn conversational agent with function calling to integrate with external APIs and business logic.
• Deploy an agent that grounds responses using Bing search results for real-time information retrieval.
• Implement an agent that manages file uploads and searches over document collections using vector stores.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Build and deploy AI agents on Azure using models from OpenAI, Microsoft, and other LLM providers, with support for tools like file search, code interpretation, and function calling.

Yes. The package is actively maintained, has low install friction, carries a permissive MIT license, and addresses a clear need for developers building agents on Azure. It supports current Python versions (3.9+), integrates with standard Azure authentication patterns, and offers both sync and async APIs. No known security vulnerabilities. Suitable for production use if you are committed to the Azure ecosystem; not a good fit if you need multi-cloud or on-premises agent infrastructure.

Install

azure-ai-agents on PyPI

pip install azure-ai-agents

uv add azure-ai-agents

poetry add azure-ai-agents

Installing azure-ai-agents

Before you install

Low install friction with three lightweight runtime dependencies (isodate, azure-core, typing-extensions). Active maintenance with recent releases; last commit 2026-08-14 and 5588 repository stars indicate ongoing development.

License in practice

MIT License permits commercial and private use with minimal restrictions; you must include a copy of the license and copyright notice in distributions.

Quickstart

pip install azure-ai-agents

import os
from azure.ai.agents import AgentsClient
from azure.identity import DefaultAzureCredential

agents_client = AgentsClient(
    endpoint=os.environ["PROJECT_ENDPOINT"],
    credential=DefaultAzureCredential(),
)
agent = agents_client.create_agent(
    model=os.environ["MODEL_DEPLOYMENT_NAME"],
    name="my-agent",
    instructions="You are helpful agent",
)

Requires Python 3.9 or later, an Azure subscription, an Azure AI Foundry project, and Entra ID authentication via DefaultAzureCredential (which requires Azure CLI and az login).

Verify before relying

• Whether the package works standalone or if azure-ai-projects is effectively required for production use cases.
• Performance characteristics and latency expectations for agent creation and message processing.
• Cost implications of using Azure AI Agents Service beyond the SDK itself.

Package facts

Evidence: azure_ai_agents-1.1.0-py3-none-any.whl

Keywords: azure, azure sdk

Tags

More Artificial Intelligence packages

Further reading