multi-agent-architecture

olivenet-iot's avatarfrom olivenet-iot

Multi-agent sistem mimarisi referansi. Use when working with agents, pipelines, or understanding the content generation workflow.

⭐0stars🔀0forks📁View on GitHub🕐Updated Dec 28, 2025⬇️1downloads
[Tool Routing and Orchestration]

When & Why to Use This Skill

This Claude skill provides a comprehensive reference for multi-agent system architecture, specifically designed for orchestrating complex AI workflows and automated content generation pipelines. It outlines a modular framework featuring specialized agent roles—such as Orchestrator, Planner, Creator, and Reviewer—to streamline the transition from initial ideation to final publication with integrated quality control and human-in-the-loop approval stages.

Use Cases

  • Architecting multi-agent systems: Use the defined roles and BaseAgent patterns to build scalable AI teams that handle specialized tasks like planning, content creation, and performance analytics.
  • Automated Content Pipelines: Implement structured workflows for social media automation (e.g., Instagram, Telegram) that include automated visual generation and multi-stage approval gates.
  • State Management and Error Handling: Utilize the provided pipeline state machine and exponential backoff retry logic to ensure robust execution of long-running agentic processes.
  • Quality Assurance Integration: Deploy a dedicated 'Reviewer' agent role to perform automated quality checks and scoring before content is published to production environments.
namemulti-agent-architecture
descriptionMulti-agent sistem mimarisi referansi. Use when working with agents, pipelines, or understanding the content generation workflow.

Multi-Agent Architecture

Agent Overview

Agent Role Key Action
Orchestrator Koordinasyon plan_week, daily_check
Planner Konu secimi suggest_topic
Creator Icerik uretimi create_post, create_visual_prompt
Reviewer Kalite kontrol review_post (score 1-10)
Publisher Platform yayin publish
Analytics Performans takip fetch_metrics

Pipeline Types

Type Telegram Approval
daily Yes (each stage)
autonomous No (min_score check)
reels Yes
carousel Yes

Daily Pipeline Flow

Planner → suggest_topic
    ↓ Telegram approval
Creator → create_post
    ↓ Telegram approval
Creator → create_visual_prompt → Flux/Veo
    ↓ Telegram approval
Reviewer → review_post (score)
    ↓ Telegram approval
Publisher → Instagram

Pipeline States

IDLE → PLANNING → AWAITING_TOPIC_APPROVAL →
CREATING_CONTENT → AWAITING_CONTENT_APPROVAL →
CREATING_VISUAL → AWAITING_VISUAL_APPROVAL →
REVIEWING → AWAITING_FINAL_APPROVAL →
PUBLISHING → COMPLETED | ERROR

Basic Usage

from app.scheduler.pipeline import ContentPipeline

pipeline = ContentPipeline(telegram_callback=callback)

# Daily (with approvals)
result = await pipeline.run_daily_content()

# Autonomous (no approvals, min_score=7)
result = await pipeline.run_autonomous_content(min_score=7)

# Reels
result = await pipeline.run_reels_content()

BaseAgent Pattern

from app.agents.base_agent import BaseAgent

class MyAgent(BaseAgent):
    def __init__(self):
        super().__init__("myagent")  # Loads persona

    async def execute(self, input_data):
        response = await self.call_claude_with_retry(
            prompt="...",
            timeout=120,
            max_retries=3
        )
        return json.loads(response)

Retry Logic

@retry_with_backoff(max_retries=3, base_delay=2.0)
# Delays: 2s, 4s, 8s (exponential)

Return Format

# Success
{"success": True, "post_id": 123, "instagram_post_id": "..."}

# Error
{"success": False, "error": "...", "final_state": "error"}
  • app/scheduler/pipeline.py - Pipeline logic
  • app/agents/base_agent.py - Base class
  • app/agents/creator.py - Content creation
  • app/agents/reviewer.py - Quality control
  • context/agent-personas/ - Agent personas