azure-ai-projects
Microsoft Corporation Azure AI Projects 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 provides a comprehensive, well-documented interface to Microsoft Foundry. It is suitable for production use of stable features. If you are building AI agents on Azure or need to manage Foundry resources programmatically, this is the standard choice. Be aware that preview features are subject to change and should not be used in production without careful testing.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.9 or later, an Azure subscription, a Microsoft Foundry project, and Entra ID authentication via DefaultAzureCredential (typically requires Azure CLI and az login).
- Low installation friction with a pure-Python wheel.
- Actively maintained with a release 18 days ago.
License · maintenance · safety
MIT (permissive) — MIT license permits unrestricted use, modification, and distribution with minimal restrictions—suitable for both commercial and open-source projects.
last release 2026-07-27 (18 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 11,517,912 downloads/mo, #1,388 on PyPI
Alternatives
Verify before relying
pip install azure-ai-projects
import os
from azure.ai.projects import AIProjectClient
from azure.identity import DefaultAzureCredential
with DefaultAzureCredential() as credential:
client = AIProjectClient(
endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
credential=credential
)- Whether async support requires aiohttp as an optional dependency or if it is bundled.
- Performance characteristics when managing large numbers of agents or datasets.
- Stability guarantees for preview features marked as such in the API.
What it is and what it does
The azure-ai-projects package is the Python client for Microsoft Foundry, a managed AI platform on Azure. It provides programmatic access to Foundry projects, allowing you to create and run agents (including containerized Hosted Agents), attach specialized tools and integrations, manage toolboxes, datasets, search indexes, and AI model deployments. The package wraps the Foundry v1 REST API and includes both stable and preview features; preview capabilities require setting allow_preview=True or accessing them through .beta sub-clients.
Typically used by developers building AI applications on Azure who need to orchestrate agents, manage resources, and integrate with Azure services like Storage, Search, Functions, and Fabric. The package depends on azure-core for HTTP handling, azure-identity for Entra ID authentication, openai for LLM operations, and azure-storage-blob for document management. It supports synchronous and asynchronous workflows and is actively maintained with support for Python 3.9 through 3.14.
Use it for
- Build and deploy multi-agent systems that leverage Azure's managed hosting and scaling infrastructure.
- Create agents with specialized tools (search, code execution, web browsing, image generation) without managing infrastructure.
- Fine-tune AI models on your own data and manage model deployments within a Foundry project.
- Manage datasets, search indexes, and document uploads for retrieval-augmented generation (RAG) workflows.
- Integrate agents with external systems via OpenAPI, Azure Functions, and Microsoft Fabric for enterprise automation.
- Evaluate and monitor generative AI application performance using built-in evaluation rules and red-team scanning.
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 provides a comprehensive, well-documented interface to Microsoft Foundry. It is suitable for production use of stable features. If you are building AI agents on Azure or need to manage Foundry resources programmatically, this is the standard choice. Be aware that preview features are subject to change and should not be used in production without careful testing.
Install
azure-ai-projects on PyPI
Before you install
Low installation friction with a pure-Python wheel. Actively maintained with a release 18 days ago. Depends on established Azure SDK packages (azure-core, azure-identity, azure-storage-blob) and openai, all standard in the ecosystem.
Requires Python 3.9 or later, an Azure subscription, a Microsoft Foundry project, and Entra ID authentication via DefaultAzureCredential (typically requires Azure CLI and az login).
License in practice
MIT license permits unrestricted use, modification, and distribution with minimal restrictions—suitable for both commercial and open-source projects.
Quickstart
pip install azure-ai-projects
import os
from azure.ai.projects import AIProjectClient
from azure.identity import DefaultAzureCredential
with DefaultAzureCredential() as credential:
client = AIProjectClient(
endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
credential=credential
)Verify before relying
- Whether async support requires aiohttp as an optional dependency or if it is bundled.
- Performance characteristics when managing large numbers of agents or datasets.
- Stability guarantees for preview features marked as such in the API.
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release >=3.9 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 6 packagesisodateazure-coretyping-extensionsazure-identityopenaiazure-storage-blob |
| Maintenance | Actively maintained 18 days since the last release |
| First released | |
| Downloads | 11,517,912 / month, #1,388 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/StableProgramming Language :: PythonProgramming Language :: Python :: 3Programming Language :: Python :: 3 :: OnlyProgramming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Programming Language :: Python :: 3.9 |
Evidence: azure_ai_projects-2.4.0-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 project management”
- azure-ai-projectsProvides a Python client for Microsoft Foundry projects, enabling…
- agent-framework-foundryProvides Microsoft Foundry integrations for the Agent Framework,…
- azure-mgmt-batchaiManages Azure Batch AI resources (clusters, jobs, experiments,…
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 agent-framework-foundry · azure-ai-agents · azure-ai-inference · foundry-platform-sdk · langchain-azure-ai · azure-ai-vision-imageanalysis · azure-ai-agentserver-core · agent-framework · azure-ai-agentserver-responses · foundry-local-sdk