$npx skillfedfor your agent

agent-framework-foundry

Microsoft Foundry integrations for Microsoft Agent Framework.

Worth itPyPI Application FrameworksReleased Aug 2026580.2K downloads / mopermissive licensePure Python

Decision gist · record as of 2026-08-14

pure-Python wheel — agent_framework_foundry-1.11.0-py3-none-any.whl
v1.11.0 · released 2026-08-14 · Python >=3.10 · 5 runtime deps: agent-framework-core, agent-framework-openai, aiohttp, azure-ai-inference, azure-ai-projects

Yes. The package is actively maintained, has no known vulnerabilities, and low install friction. It is the official bridge between the open-source Agent Framework and Microsoft's Foundry platform, so if you are building agents on Azure Foundry or need to integrate Foundry-hosted tools into Python agents, this is the required integration layer. If you are not using Azure Foundry, it is not applicable.AI-flagged interpretation of the facts on this page — verify before relying

Before you install

  • Requires Python 3.10 or later and valid Azure Foundry credentials (project endpoint and authentication).
  • Active maintenance with a recent release (2026-08-14) and no known vulnerabilities.
  • Low install friction with a pure-Python wheel.

License · maintenance · safety

permissive license (permissive) — Licensed under MIT (permissive), so you can use, modify, and distribute this package freely with minimal restrictions.

last release 2026-08-14 (0 days) · last repo commit 2026-08-14 · 12,804 stars

0 known vulnerabilities (OSV.dev, 2026-08-14) · 580,194 downloads/mo, #5,913 on PyPI

Verify before relying

pip install agent-framework-foundry

from agent_framework import Agent
from agent_framework.foundry import FoundryChatClient

async with Agent(
    client=FoundryChatClient(...),
    instructions="You are a helpful assistant.",
    tools=[FoundryChatClient.get_web_search_tool()],
) as agent:
    result = await agent.run("What tools are available?")
    print(result.text)
  • Whether azure-ai-projects>=2.1.0 is required for all toolbox features or only for authoring APIs.
  • Performance characteristics and latency expectations when calling hosted Foundry tools.
  • Exact scope of experimental features (FOUNDRY_TOOLS, FOUNDRY_PREVIEW_TOOLS, TO_PROMPT_AGENT) and their stability timeline.
Same gist for agents: .md · .json

What it is and what it does

Agent Framework Foundry is a Python SDK layer that bridges the open-source Agent Framework with Microsoft's hosted Foundry platform on Azure. It provides chat clients, preconfigured agents, and memory providers that connect to Foundry-managed resources, allowing you to build and deploy AI agents that leverage hosted tools (code interpreter, web search, file search, image generation, MCP servers) without managing infrastructure yourself.

The package centers on two main patterns: FoundryAgent for agents already deployed in a Foundry project (which invoke tools transparently through the service), and FoundryChatClient for local agents that connect to Foundry toolboxes and hosted tool factories over MCP or direct API calls. It also includes utilities to convert a locally-defined Agent into a Foundry PromptAgentDefinition for publishing back to the platform, keeping your agent definition as a single source of truth.

Use it for

  • Build a multi-turn conversational agent that uses web search, code execution, and file analysis without hosting those tools yourself.
  • Manage reusable tool configurations (toolboxes) once in Foundry and attach them to multiple agents across your organization.
  • Convert a locally-tested Agent into a hosted Foundry prompt agent for production deployment without rewriting configuration.
  • Integrate Foundry-hosted agents into Python applications that need to call external tools like SharePoint, Fabric, or custom MCP servers.
  • Create agents that leverage Azure AI Search, Bing grounding, or computer-use capabilities through factory methods.

Worth the install?

AI-flagged interpretation of the facts on this page. Verify before relying on it.

Worth it

Yes.

The package is actively maintained, has no known vulnerabilities, and low install friction. It is the official bridge between the open-source Agent Framework and Microsoft's Foundry platform, so if you are building agents on Azure Foundry or need to integrate Foundry-hosted tools into Python agents, this is the required integration layer. If you are not using Azure Foundry, it is not applicable.

Install

agent-framework-foundry on PyPI

Before you install

Active maintenance with a recent release (2026-08-14) and no known vulnerabilities. Low install friction with a pure-Python wheel. Depends on agent-framework-core, agent-framework-openai, aiohttp, and two Azure AI packages, all of which are standard dependencies in the Azure SDK ecosystem.

Requires Python 3.10 or later and valid Azure Foundry credentials (project endpoint and authentication).

License in practice

Licensed under MIT (permissive), so you can use, modify, and distribute this package freely with minimal restrictions.

Quickstart

pip install agent-framework-foundry

from agent_framework import Agent
from agent_framework.foundry import FoundryChatClient

async with Agent(
    client=FoundryChatClient(...),
    instructions="You are a helpful assistant.",
    tools=[FoundryChatClient.get_web_search_tool()],
) as agent:
    result = await agent.run("What tools are available?")
    print(result.text)

Verify before relying

  • Whether azure-ai-projects>=2.1.0 is required for all toolbox features or only for authoring APIs.
  • Performance characteristics and latency expectations when calling hosted Foundry tools.
  • Exact scope of experimental features (FOUNDRY_TOOLS, FOUNDRY_PREVIEW_TOOLS, TO_PROMPT_AGENT) and their stability timeline.

Package facts

Licensepermissive license permissive
Python supportSupports the current Python release >=3.10
Install frictionLow. Pure-Python wheel
Runtime dependencies
5 packages
agent-framework-coreagent-framework-openaiaiohttpazure-ai-inferenceazure-ai-projects
MaintenanceActively maintained 0 days since the last release
Last repo commit
First released
Downloads580,194 / month, #5,913 on PyPI 30-day window, as of 2026-08-14
Known vulnerabilitiesNone known OSV.dev, checked 2026-08-14
Classifiers
Development Status :: 5 - Production/StableIntended Audience :: DevelopersLicense :: OSI Approved :: MIT LicenseProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Typing :: Typed

Evidence: agent_framework_foundry-1.11.0-py3-none-any.whl

Tags

Capabilities
azure foundry agent integrationmicrosoft agent framework toolsfoundry chat client pythonazure ai agents sdkfoundry toolbox managementhosted agent deploymentazure ai project agents
Topics
azure-aiagent-frameworkfoundry-integration

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 foundry agent integration”

Give your agent the search over MCP, or paste the wish link into any chat.

More Application Frameworks packages

fastapi Worth it
PyPI · Software Development · released Jul 2026

FastAPI is a Python web framework for building REST APIs using type hints, with automatic request validation, serialization, and interactive API documentation.

MITpure Python · 3.10+
568.6Mdownloads / mo
annotated-doc With conditions
PyPI · Software Development · released Jul 2026

Provides a way to document function parameters, class attributes, return types, and variables inline using Python's `Annotated` type hint syntax instead of traditional docstrings.

MITpure Python · 3.9+
456.2Mdownloads / mo
textual Worth it
PyPI · Application Frameworks · released Jun 2026

Textual is a Python framework for building cross-platform user interfaces that run in the terminal or web browser using a modern, component-based API.

Install it if you're developing CLI tools, dashboards, or interactive terminal applications.

MITpure Python
443.6Mdownloads / mo
typer Worth it
PyPI · Software Development · released Aug 2026

Typer builds command-line applications from Python functions using type hints, automatically generating help text, argument parsing, and shell completion.

Install it if you are building CLIs in Python.

MITpure Python · 3.10+
369.3Mdownloads / mo
mcp Worth it
PyPI · Application Frameworks · released Jul 2026

Build and connect to Model Context Protocol servers that expose tools, resources, and prompts to LLM applications over stdio, HTTP, or SSE transports.

Install it if you need to build or connect to servers.

MITpure Python · 3.10+
319.3Mdownloads / mo
Werkzeug Worth it
PyPI · Application Frameworks · released Apr 2026

Werkzeug is a WSGI utility library providing request/response objects, URL routing, an interactive debugger, HTTP utilities, and a development server for building web applications.

BSD-3-Clausepure Python · 3.9+
268.1Mdownloads / mo

See also agent-framework-declarative · agent-framework-foundry-local · azure-ai-projects · foundry-platform-sdk · agent-framework-azure-ai · agent-framework-foundry-hosting · agent-framework · langchain-azure-ai · agent-framework-claude · agent-framework-ollama

Further reading