Skip to content
Agent

Hierarchical Agent System

by AntonTegnelov

AI Summary

A multi-agent architecture that organizes AI agents into a hierarchy (Architect, Planner, Executor) to decompose and solve complex problems through structured delegation. Developers building sophisticated AI systems that require task decomposition and specialized agent roles will benefit from this reusable framework.

Install

Copy this and paste it into Claude Code, Cursor, or any AI assistant:

I want to set up the "Hierarchical Agent System" agent in my project.

Please run this command in my terminal:
# Add AGENTS.md to your project root
curl --retry 3 --retry-delay 2 --retry-all-errors -o AGENTS.md "https://raw.githubusercontent.com/AntonTegnelov/agentic_problem_solver/main/docs/explanation/hierarchical_agents.md"

Then explain what the agent does and how to invoke it.

Description

An multi-agent AI problem solver

Overview

The hierarchical agent system is a protocol-based architecture that organizes agents into a structured hierarchy with specialized roles. This design enables more effective task decomposition, delegation, and execution compared to a single-agent approach. The system follows a top-down structure where higher-level agents break down complex tasks and delegate them to specialized agents with specific capabilities.

Key Capabilities

• Parent-Child Relationships: Register, retrieve, and manage parent-child connections between agents • Hierarchical Queries: Find parent, child, and sibling agents • Capability-Based Discovery: Locate agents with specific capabilities • Agent Hierarchy Visualization: Generate a complete view of the agent hierarchy

Agent Roles

The hierarchical system defines three primary agent roles:

1. Architect Agent (`ArchitectAgent`)

• Purpose: High-level system design and task decomposition • Responsibilities: • Breaking down complex problems into major components • Making architectural decisions • Delegating component implementation to Planner Agents • Ensuring overall system coherence • Capabilities: System design, architecture planning, component identification • Position in Hierarchy: Top-level agent, parent to Planner Agents

Discussion

0/2000
Loading comments...

Health Signals

MaintenanceCommitted 1y ago
Dead
AdoptionUnder 100 stars
0 ★ · Niche
DocsMissing or thin
Undocumented

GitHub Signals

Issues0
Updated1y ago
View on GitHub
MIT License

My Fox Den

Community Rating

Sign in to rate this booster

Works With

Claude Code
Claude.ai