Agent Framework Azure Ai Py

This is a Python SDK wrapper for building persistent agents on Azure AI Foundry, giving you the full Microsoft Agent Framework with cloud-hosted state management. You get conversation threads that survive between sessions, built-in tools like code execution and Bing search, and proper async context managers for credential handling. The structured outputs with Pydantic validation are clean, and being able to pass Python functions directly as tools without manual schema wrangling is nice. It's overkill if you just need a one-off LLM call, but if you're building multi-turn agents that need to remember context across sessions or integrate with Azure's hosted tooling, this handles the persistence layer so you don't have to roll your own thread storage.

skills.sh installs: 145
GitHub stars: 39.4K
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add sickn33/antigravity-awesome-skills --skill agent-framework-azure-ai-py --agent claude-code

Installs into .claude/skills of the current project.

Files

Bundled upstream support

Supporting files are included at skill-relative paths. See UPSTREAM-NOTICE.md for their pinned sources, licenses, hashes, and import changes.

Agent Framework Azure Hosted Agents

Build persistent agents on Azure AI Foundry using the Microsoft Agent Framework Python SDK.

Architecture

User Query → AzureAIAgentsProvider → Azure AI Agent Service (Persistent)
                    ↓
              Agent.run() / Agent.run_stream()
                    ↓
              Tools: Functions | Hosted (Code/Search/Web) | MCP
                    ↓
              AgentThread (conversation persistence)