hybrid-agents

Community

Orchestrate cloud and local agents end-to-end.

Authorsamelhousseini
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill enables teams to design and run production-grade multi-agent workflows that combine local client-side orchestration with cloud-managed agents, enabling scalable, privacy-conscious AI automation.

Core Features & Use Cases

  • Multi-agent orchestration: supports sequential, parallel (fan-out/fan-in), and hybrid patterns across Microsoft Agent Framework and Azure AI Foundry.
  • MCP integration: enables tool calls and approvals for external services within agent workflows.
  • Production resilience: includes retry with backoff, circuit breaker, and workflow checkpointing for long-running processes.
  • Use Case: implement a cloud+local data processing pipeline that runs locally for sensitive data and leverages cloud reasoning for scale.

Quick Start

Run the hybrid workflow demo with real Azure credentials. Example steps:

  1. Configure environment variables (PROJECT_ENDPOINT, AZURE_OPENAI_ENDPOINT, AZURE_OPENAI_CHAT_DEPLOYMENT_NAME, MODEL_DEPLOYMENT_NAME).
  2. Install dependencies from requirements.txt.
  3. Run the v1 demo: python scripts/hybrid_workflow_demo.py
  4. Or run the v2 demo: python scripts/hybrid_workflow_demo_v2.py

Dependency Matrix

Required Modules

agent-frameworkazure-ai-agentsazure-ai-projectsazure-identitypython-dotenv

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: hybrid-agents
Download link: https://github.com/samelhousseini/microhacks/archive/main.zip#hybrid-agents

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.