agent-framework-openai
OpenAI integrations for Microsoft Agent Framework.
What it is and what it does
agent-framework-openai is a bridge between Microsoft's Agent Framework and OpenAI's APIs, providing three main client classes: OpenAIChatClient (using the Responses API), OpenAIChatCompletionClient (using the Chat Completions API), and OpenAIEmbeddingClient. It abstracts authentication and model selection for both OpenAI and Azure OpenAI deployments, allowing you to configure clients via environment variables or direct parameters.
The package is designed for developers building agent-based applications who want to integrate OpenAI's language models without managing API details directly. It depends on agent-framework-core (the base framework) and openai (the official SDK), and supports multiple Python versions from 3.10 onward. The documentation recommends using OpenAIChatClient for new work unless you have a specific reason to use the Chat Completions API.
Use it for:
- Build agent applications that call OpenAI's latest models via the Responses API without writing boilerplate authentication code.
- Migrate existing Chat Completions-based integrations to the Agent Framework while maintaining API compatibility.
- Generate embeddings for documents or queries using OpenAI's embedding models within an agent workflow.
- Deploy agents to Azure OpenAI by configuring credentials and endpoints through environment variables or constructor parameters.
- Switch between OpenAI and Azure OpenAI deployments by toggling environment variables without code changes.
Worth the install?
AI-flagged interpretation of the facts on this page — verify before relying
Provides OpenAI and Azure OpenAI integration for Microsoft Agent Framework, with chat clients using the Responses API or Chat Completions API, plus an embedding client.
Yes. The package is actively maintained, has low install friction, carries a permissive license, and integrates cleanly into the Agent Framework ecosystem. It is suitable for production use if you are already using Microsoft Agent Framework and need OpenAI integration. No security vulnerabilities are recorded. Install it if you are building agents with OpenAI models; skip it if you do not use the Agent Framework or prefer direct OpenAI SDK calls.
Install
agent-framework-openai on PyPI
pip
pip install agent-framework-openaiuv
uv add agent-framework-openaipoetry
poetry add agent-framework-openaiInstalling agent-framework-openai
Before you install
Low install friction with only two runtime dependencies. Active maintenance as of 2026-08-14 with recent release history since 2026-03-30. Supports current Python versions (3.10–3.14).
License in practice
Permissive license treatment allows use in most commercial and open-source projects without significant restrictions.
Quickstart
pip install agent-framework-openai
from agent_framework.openai import OpenAIChatClient
client = OpenAIChatClient(model="gpt-4.1")
Requires OPENAI_API_KEY environment variable or explicit credentials (e.g., Azure credential) to authenticate with OpenAI or Azure OpenAI.
Verify before relying
- Whether agent-framework-core and openai versions have known compatibility constraints beyond what the fact sheet shows.
- Performance characteristics or rate-limit handling behavior of the chat and embedding clients.
- Whether the Responses API is production-ready or still evolving in the upstream OpenAI SDK.
Package facts
| License | not declared (permissive) |
| Python support | supports the current Python release (>=3.10) |
| Install friction | low — pure-Python wheel |
| Runtime dependencies | 2 — agent-framework-core, openai |
| Maintenance | actively maintained — 0 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 973,743/month — #4,602 on PyPI (30-day window, as of 2026-08-14) |
| Known vulnerabilities | none known (OSV.dev, checked 2026-08-14) |
Evidence: agent_framework_openai-1.13.0-py3-none-any.whl
Tags
More Application Frameworks packages
FastAPI is a Python web framework for building…
permissive · top 100 on PyPI
annotated-docProvides a way to document function parameters,…
permissive · top 100 on PyPI
textualTextual is a Python framework for building…
permissive · top 100 on PyPI
typerTyper builds command-line applications from…
permissive · top 1,000 on PyPI
mcpBuild and connect to Model Context Protocol…
permissive · top 1,000 on PyPI
WerkzeugWerkzeug is a WSGI utility library providing…
permissive · top 1,000 on PyPI
agent-frameworkBuilds and orchestrates AI agents powered by…
permissive · top 5,000 on PyPI
agent-framework-purviewAdds Microsoft Purview data governance and DLP…
permissive · top 15,000 on PyPI
agent-framework-devuiProvides a lightweight web UI and…
permissive · top 15,000 on PyPI
agent-framework-chatkitBridges Microsoft Agent Framework agents with…
permissive · top 15,000 on PyPI
composio-openaiBridges Composio's tool ecosystem to OpenAI's…
permissive · top 15,000 on PyPI
llm-openai-pluginA plugin that extends LLM to access OpenAI…
permissive · top 15,000 on PyPI
agent-framework-coreBuild, orchestrate, and deploy AI agents and…
permissive · top 5,000 on PyPI
azure-ai-inferenceUnified client library for chat completions,…
permissive · top 5,000 on PyPI
openai-messages-token-helperEstimates token usage for OpenAI Chat…
permissive · top 15,000 on PyPI
azure-ai-agentserver-responsesProvides the Responses protocol endpoints for…
permissive · top 15,000 on PyPI