memory-blackboard

Community

Shared memory for multi-agent workflows.

Authorryasrk
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill addresses the inefficiency and redundancy in multi-agent workflows by establishing a shared memory protocol, preventing duplicate work and enabling seamless context sharing between agents.

Core Features & Use Cases

  • Session Memory as Blackboard: Utilizes a structured directory (/memories/session/) for inter-agent communication, result caching, and progressive context building.
  • Reduces Token Waste: Prevents multiple agents from re-exploring the same codebase or re-deriving the same information, leading to significant token savings.
  • Enables Cross-Agent Context: Facilitates complex, multi-phase tasks where later stages depend on the outcomes of earlier ones, and supports cross-domain collaboration.
  • Use Case: In a multi-phase project (e.g., AI → Backend → Frontend), the AI phase writes its decisions to ai-phase-results.md. The Backend phase then reads this file to ensure its implementation aligns with AI requirements, avoiding rework.

Quick Start

Instruct the planner to write the initial project context to the session memory blackboard.

Dependency Matrix

Required Modules

None required

Components

references

💻 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: memory-blackboard
Download link: https://github.com/ryasrk/AgentBrokeTheMatrix-CopilotVersion/archive/main.zip#memory-blackboard

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.