genpark-blackboard-architecture-shared-memory-skill

Blackboard pattern architecture for multi-agent coordination with Knowledge Sources and prioritized agenda controller.

Part of the GenPark AI Agent Skills Matrix. Production-ready, zero external dependencies, native Python 3.9+ standard library.

Architecture

flowchart TD
    A[Environment Perception / Goal] --> B[Blackboard / BDI Deliberator]
    B --> C[Contract Net / Task DAG Pipeline]
    C --> D[Subsumption Action Execution]
    D --> E[MCP Protocol Endpoint]

Features

• Zero Third-Party Dependencies: Pure Python standard library (collections, heapq).
• Autonomous Swarm Intelligence: Blackboard pattern, Critical Path DAG scheduler, Contract Net Protocol auctions, Subsumption architecture, and BDI reasoning.
• Native MCP Protocol Support: Integrated JSON-RPC 2.0 stdio server ready for Claude Desktop, Cursor, and Windsurf.

Installation

pip install genpark-blackboard-architecture-shared-memory-skill

Or clone directly:

git clone https://github.com/alphaparkinc/genpark-blackboard-architecture-shared-memory-skill.git
cd genpark-blackboard-architecture-shared-memory-skill
python example_usage.py

Quick Start

from client import *
# Refer to example_usage.py for end-to-end execution

Model Context Protocol (MCP) Setup

Add to your claude_desktop_config.json or cursor.json:

{
  "mcpServers": {
    "genpark-blackboard-architecture-shared-memory-skill": {
      "command": "python",
      "args": ["-m", "genpark-blackboard-architecture-shared-memory-skill.mcp_server"]
    }
  }
}

License

MIT License. Copyright (c) 2026 AlphaPark Inc. & Alpha-Park.