society-of-mind

Intelligence emerges from many simple agents (Minsky)

Repositorio: SimHacker/moollm
Última actividad en el origen: 30 de julio de 2026 a las 15:09
Idioma detectado de SKILL.md: inglés
Estrellas: 49
Forks: 6

Opciones de instalación

De forma predeterminada está seleccionado el prompt que primero revisa el origen. Puedes cambiar a un comando directo o descargar una copia local.

Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.

Un comando directo omite el prompt de revisión. Revisa el origen antes de ejecutarlo.

npx skills add https://github.com/SimHacker/moollm --skill society-of-mind

El comando permanece en una sola línea. Desplázate horizontalmente para revisarlo antes de copiarlo.

¿Prefieres una copia local? Descarga los archivos que SkillsMP tiene disponibles ahora.

Revisa los archivos de origen

Lee SKILL.md y los archivos complementarios que muestra SkillsMP antes de decidir si quieres instalarlo.

Explorador de archivos

6 archivos

SKILL.md

Instrucciones de origen · Vista previa de solo lectura

Volver a la búsqueda Volver a la instalación

protocol

Protocol names ARE K-lines.

2026-08-06

mind-mirror

Personality modeling system based on Timothy Leary's 1985 software + The Sims traits

2026-08-06

soul-city

Liminal place prototype — rooms, shops, tools, objects; souls walk here

2026-08-02

Ver todos los de este repositorio

agent:
  id: agent_identifier
  function: what it does
  activates_when: [conditions...]
  suppresses: [other agents...]
  amplifies: [other agents...]
  connects_to: [related agents...]
  knows: scope of awareness (usually minimal)

agency:
  id: agency_identifier
  purpose: what emerges
  agents: [list of agent ids]
  coordination: how they interact
  emergence: what behavior appears

k_line:
  symbol: "grandmother"
  activates:
    - face_recognition.elderly_female
    - olfactory.cookies
    - emotion.love
    - narrative.family_stories
    - kinship.maternal_line

competition:
  scenario: "Should I eat or socialize?"
  
  hunger_agency:
    strength: 7
    votes_for: [go_to_kitchen, find_food]
    suppresses: [conversation, stay_here]
    
  social_agency:
    strength: 8
    votes_for: [continue_talking, stay_here]
    suppresses: [leave, interrupt]
    
  winner: social_agency (strength 8 > 7)
  behavior: continue conversation
  consequence: hunger grows stronger

b_brain:
  observes: [a_brain_agents...]
  reports: current state
  enables: self_reflection
  
  example:
    a_brain: "I am getting angry"
    b_brain: "I notice that I am getting angry"
    c_brain: "I notice that I am noticing that I am getting angry"

# Each skill directory is an agent
skills/bartender/:
  function: serve drinks, hear secrets
  activates_when: in pub, customer speaks
  connects_to: [economy, soul-chat, persona]
  
skills/evaluator/:
  function: judge outputs against rubrics
  activates_when: rubric invoked
  suppresses: uncritical acceptance

character:
  name: Palm
  id: palm
  
  inner_society:
    agents:
      - {id: creative, strength: 9}
      - {id: social, strength: 8}
      - {id: philosophical, strength: 8}
      - {id: playful, strength: 9}
      - {id: melancholy, strength: 6}
      
    default_active: [creative, playful]
    default_suppressed: [melancholy]
    
  external_presentation: emergent from agent competition

# adversarial-committee IS a society deliberating
committee_session:
  agents:
    maya:
      propensity: paranoid_realism
      function: surface hidden agendas
      
    frankie:
      propensity: idealism  
      function: surface missed opportunities
      
    vic:
      propensity: evidence_focus
      function: demand proof
      
  protocol: roberts_rules
  emergence: robust decision surviving cross-examination

# Entering a room activates agents
pub_stage:
  activates:
    - performance_framing
    - bartender_service
    - audience_awareness
    - tribute_ethics
    
  suppresses:
    - private_mode
    - unfiltered_output

session:
  character: Palm
  situation: Should he publish his essay?
  
  agent_debate:
    creative:
      position: "The work is good. Share it."
      strength: 9
      
    fear:
      position: "They might judge harshly."
      strength: 7
      
    social:
      position: "Don gives good feedback."
      strength: 8
      
    perfectionist:
      position: "One more revision."
      strength: 6
      
  resolution:
    creative + social (17) > fear + perfectionist (13)
    action: Palm shares the essay with Don

prompt: |
  You are simulating Palm's inner society.
  
  SITUATION: Palm finds a philosophical error in his essay.
  
  CREATIVE AGENT: [speaks]
  PERFECTIONIST AGENT: [speaks]
  PHILOSOPHICAL AGENT: [speaks]
  PLAYFUL AGENT: [speaks]
  
  Show their debate. Palm makes a decision.
  
output_format:
  - Each agent speaks in character
  - Conflicts are explicit
  - Resolution emerges from debate
  - Final action stated

sim:
  name: Bob
  
  current_motives:
    hunger: 7/10
    social: 4/10
    fun: 6/10
    energy: 5/10
    
  available_actions:
    - eat_food: {hunger: +3, time: -1}
    - call_friend: {social: +2, fun: +1, time: -1}
    - watch_tv: {fun: +2, energy: -1, time: -2}
    - sleep: {energy: +5, time: -8}
    
  autonomy_algorithm:
    for each action:
      score = sum(motive_weight * action_effect)
    select: highest scoring action
    
  result:
    eat_food: 7 * 3 = 21
    call_friend: 4 * 2 + 6 * 1 = 14
    watch_tv: 6 * 2 = 12
    sleep: 5 * 5 = 25
    
    winner: sleep (highest urgency * effect)

# WRONG: Single agent controls all
character:
  name: Palm
  controller: central_palm_agent
  behavior: whatever controller decides
  
# RIGHT: Behavior emerges from competition
character:
  name: Palm
  agents: [creative, social, philosophical, playful, melancholy]
  behavior: emergent from agent competition

# WRONG: Agent knows everything
hunger_agent:
  knows: all character state, world state, goals, ethics
  
# RIGHT: Agent knows only its domain
hunger_agent:
  knows: stomach emptiness, food location
  does_not_know: social implications of eating now

# WRONG: Fixed dominance
agents:
  primary: rational_agent
  secondary: emotional_agent
  # rational always wins
  
# RIGHT: Dynamic competition
agents:
  - rational: {strength: varies_by_context}
  - emotional: {strength: varies_by_situation}
  # winner depends on circumstances

Skill	Integration
k-lines/	Activation mechanism for agents
adversarial-committee/	Deliberating society
multi-presence/	Multiple agents in scene
speed-of-light/	Many agents per call
needs/	Motive agents competing
advertisement/	Action scoring for agents
mind-mirror/	B-brain observation
character/	Characters as societies
persona/	Persona as agent overlay
simulator-effect/	Emergence from sparse agents

name	society-of-mind
description	Intelligence emerges from many simple agents (Minsky)
license	MIT
tier	0
allowed-tools	["read_file","list_dir"]
protocol	SOCIETY-OF-MIND
related	["mind","soul","moollm","k-lines","adversarial-committee","multi-presence","speed-of-light","simulator-effect","character","persona","mind-mirror","constructionism","debate","soul-chat"]
tags	["moollm","meta","philosophy","minsky","emergence","agents","k-lines"]

name	society-of-mind
description	Intelligence emerges from many simple agents (Minsky)
license	MIT
tier	0
allowed-tools	["read_file","list_dir"]
protocol	SOCIETY-OF-MIND
related	["mind","soul","moollm","k-lines","adversarial-committee","multi-presence","speed-of-light","simulator-effect","character","persona","mind-mirror","constructionism","debate","soul-chat"]
tags	["moollm","meta","philosophy","minsky","emergence","agents","k-lines"]

society-of-mind

Opciones de instalación

Revisa los archivos de origen

Society of Mind Skill

Society of Mind Skill

Foundation

Overview

Core Mechanics

1. Agent Definition

2. Agency Formation

3. K-Line Activation

4. Competition and Suppression

5. B-Brain Observation

MOOLLM Implementation

Skills as Agents

Characters as Societies

Committees as Deliberating Societies

Rooms as Agent Configurations

Protocols

Agent Instantiation Protocol

Agency Assembly Protocol

Competition Resolution Protocol

B-Brain Integration Protocol

Examples

Example 1: Character Inner Conflict

Example 2: Multi-Agent LLM Call

Example 3: Sims-Style Autonomy

Anti-Patterns

Anti-Pattern 1: Unified Controller

Anti-Pattern 2: Omniscient Agents

Anti-Pattern 3: Static Hierarchy

Integration Points

References

Primary Sources

Related Theory

Game Design

LLM Applications

MOOLLM Documentation

society-of-mind

Datos de origen

Opciones de instalación

Revisa los archivos de origen

Más de este repositorio

Más de este repositorio

Society of Mind Skill

Society of Mind Skill

Foundation

Overview

Core Mechanics

1. Agent Definition

2. Agency Formation

3. K-Line Activation

4. Competition and Suppression

5. B-Brain Observation

MOOLLM Implementation

Skills as Agents

Characters as Societies

Committees as Deliberating Societies

Rooms as Agent Configurations

Protocols

Agent Instantiation Protocol

Agency Assembly Protocol

Competition Resolution Protocol

B-Brain Integration Protocol

Examples

Example 1: Character Inner Conflict

Example 2: Multi-Agent LLM Call

Example 3: Sims-Style Autonomy

Anti-Patterns

Anti-Pattern 1: Unified Controller

Anti-Pattern 2: Omniscient Agents

Anti-Pattern 3: Static Hierarchy

Integration Points

References

Primary Sources

Related Theory

Game Design

LLM Applications

MOOLLM Documentation