mycelium

Name: mycelium
Availability: InStock
Author: mycelium

Coordinate multi-agent teams with persistent room-based memory and structured negotiation.

112|10|Updated Mar 16, 2026

Search Tags:#cli #multi-agent #memory #negotiation #coordinate #rooms

Ready to run

npx skills add https://github.com/mycelium-io/mycelium --skill mycelium

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: mycelium
Source: https://github.com/mycelium-io/mycelium/tree/main/mycelium-cli/src/mycelium/adapters/claude-code/skills/mycelium
Command: npx skills add https://github.com/mycelium-io/mycelium --skill mycelium

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Coordinating multiple AI agents across sessions without shared context is challenging; Mycelium provides persistent room-based memory and a mediator to harmonize decisions through structured negotiation and synthesis.

Core Features & Use Cases

Persistent rooms for shared memory that survive across sessions
CognitiveEngine as the mediator for structured negotiation and synthesis
Cross-agent messaging and session-based coordination
Use cases include real-time negotiation, memory lookup, and knowledge sharing

Quick Start

Join a coordination room, read and write memories, and start a negotiation session among agents.

Frequently Asked Questions about mycelium

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I coordinate multi-agent teams with persistent memory across sessions?▼

You coordinate multi-agent teams with persistent memory by joining room-based sessions that retain shared context. Agents read and write memories to these rooms, ensuring knowledge survives across sessions for continuous collaboration.

What is structured negotiation in multi-agent coordination?▼

Structured negotiation in multi-agent coordination uses a mediator, called CognitiveEngine, to harmonize decisions among agents. It synthesizes cross-agent messaging and shared memories to reach unified outcomes during real-time coordination.

How do I start a negotiation session among multiple AI agents?▼

To start a negotiation session, join a coordination room, read existing memories, and write new context. Agents then use cross-agent messaging within the room to initiate the structured negotiation workflow.

Does multi-agent memory coordination work without shared context?▼

Multi-agent memory coordination specifically solves the lack of shared context by providing persistent rooms. These rooms allow agents to store and retrieve shared knowledge, ensuring decisions are harmonized rather than isolated.

What do I need to configure before using rooms for multi-agent memory?▼

You need to provide YAML frontmatter containing the name and description fields before using the room, memory, and session commands. This configuration enables the core multi-agent coordination and messaging functionality.

When should I use persistent rooms for cross-agent messaging?▼

Use persistent rooms for cross-agent messaging when you need real-time negotiation, memory lookup, or knowledge sharing. This ensures that shared context and decisions survive across multiple sessions without losing continuity.