azure-ai-agents
Microsoft Corporation Azure AI Agents Client Library for Python
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- 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).
- 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 · maintenance · safety
MIT License (permissive) — MIT License permits commercial and private use with minimal restrictions; you must include a copy of the license and copyright notice in distributions.
last release 2025-08-05 (374 days) · last repo commit 2026-08-14 · 5,588 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 7,601,444 downloads/mo, #1,716 on PyPI
Alternatives
Verify before relying
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",
)- 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.
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 on it.
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
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.
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).
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",
)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
| License | MIT License permissive |
| Python support | Supports the current Python release >=3.9 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 3 packagesisodateazure-coretyping-extensions |
| Maintenance | Actively maintained 374 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 7,601,444 / month, #1,716 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 5 - Production/StableLicense :: OSI Approved :: MIT LicenseProgramming Language :: PythonProgramming Language :: Python :: 3Programming Language :: Python :: 3 :: OnlyProgramming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.9 |
Evidence: azure_ai_agents-1.1.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “azure ai agents client”
- azure-ai-agentsBuild and deploy AI agents on Azure using models from OpenAI,…
- azure-ai-projectsProvides a Python client for Microsoft Foundry projects, enabling…
- agent-framework-foundryProvides Microsoft Foundry integrations for the Agent Framework,…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also azure-ai-projects · azure-ai-vision-imageanalysis · azure-ai-inference · azure-search-documents · agent-framework-ollama · agent-framework-foundry · azure-mgmt-resource-deployments · agent-framework · agent-framework-foundry-local · microsoft-agents-a365-runtime