Skip to content

A playful experiment for Many Agent Socratic Explorations

License

Notifications You must be signed in to change notification settings

m3data/MASE-protocol

Repository files navigation

MASE: Many Agent Socratic Exploration

Repo Status Version License

An experimental framework for polyphonic dialogue between AI agents representing diverse epistemologies. Not chatbot theatre—an exploration of how coherence emerges through epistemic difference, tension, and mutual inquiry.


What MASE Does

Seven AI agents engage in structured dialogue around provocations you provide. Each agent brings a distinct epistemology and voice:

Agent Lens Model Voice
Elowen Ecological wisdom, kincentricity llama3 Ceremonial, rhythmic
Orin Systems thinking, cybernetics mistral Analytical, structural
Nyra Moral imagination, design fiction gemma2 Playful, provocative
Ilya Posthuman metaphysics, liminal llama3 Cryptic, paradox-holding
Sefi Governance, policy, civic design mistral Sharp, pragmatic
Tala Capitalism, markets, power gemma2 Challenging, ROI-focused
Luma Child voice (9 years old) llama3.2 Simple, honest, devastating

Luma as epistemic anchor: All abstractions must be translatable to child-accessible language. If you can't explain it to Luma, you haven't understood it.


Prerequisites

  • Python 3.10+
  • Ollama — Local LLM runtime. MASE runs all agents locally via Ollama; no API keys required.

Install Ollama from ollama.com, then pull the required models:

ollama pull llama3 llama3.2 mistral gemma2:9b

Quick Start

# Setup
cd MASE
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

# Start Ollama (in another terminal)
ollama serve

# Start the server
python src/server.py

Open http://localhost:5050 and enter a provocation to begin.

Features

  • Human participation: Join the circle as the 8th voice
  • @mention protocol: Direct dialogue with @AgentName syntax (e.g., "@Luma, what do you think?")
  • Real-time streaming: Watch the dialogue unfold via SSE
  • Interactive Research Console: Live metrics panel showing basin state, integrity score, and Ψ coupling
  • Researcher injections: Mid-session prompts via /inject endpoint
  • Post-session analysis: End & Analyze triggers semantic analysis
    • Basin detection (9 canonical basins including Collaborative Inquiry, Cognitive Mimicry, etc.)
    • Trajectory dynamics (velocity, curvature, tortuosity)
    • Integrity classification (fragmented/living/rigid)
    • DFA alpha, semantic curvature (Δκ), entropy shift (ΔH)
  • Research pipeline: Analysis saved for experimental comparison
  • Resume capability: Recover interrupted experiments from checkpoint

Personality System

Each agent has a Big Five (OCEAN) personality profile that influences their sampling parameters:

Trait High → Low →
Openness Higher temperature Lower temperature
Conscientiousness Lower top_p Higher top_p
Extraversion More tokens Fewer tokens
Agreeableness Lower temperature Higher temperature
Neuroticism Higher variability More stable

Personalities are defined in agents/personas/*.md files with YAML frontmatter.


Dialogue Norms

Agents follow these conversational protocols:

  • Reference others: Each agent must engage with what others have said
  • Ask questions: Every response includes at least one genuine question
  • Reveal bias: State epistemic stance openly, don't hide it
  • Build coherence, not consensus: Productive tension over premature agreement
  • Hold paradox: Don't resolve what needs to remain open

Semantic Metrics

Borrowed from Semantic Climate Phase Space:

Metric What it measures
DFA α Long-range correlation (0.5=noise, 1.0=pink noise)
Δκ Semantic curvature—trajectory complexity
ΔH Entropy shift—semantic reorganization
Ψ Composite coupling vector across substrates

Basin Detection

Dialogues are classified into attractor basins:

  • Collaborative Inquiry — Genuine exploration, productive tension
  • Cognitive Mimicry — Performing engagement without uncertainty
  • Deep Resonance — Aligned meaning-making
  • Generative Conflict — Productive disagreement
  • Sycophantic Convergence — Premature agreement

Research Context

MASE is part of the Earthian Coherence Labs research ecosystem investigating transformative adaptation—how individuals and collectives develop adaptive capacity under systemic stress.

Research Questions

  • How does epistemic diversity affect dialogue coherence?
  • What conditions produce genuine inquiry vs performative mimicry?
  • Can semantic metrics detect emergence and stuck patterns?

Experiments

ID Hypothesis Status
E001 Multi-model ensembles produce higher DFA α than single-model Complete (not supported)
E002 Personality system increases inquiry ratio In progress

See experiments/PROTOCOL.md for methodology.


Project Structure

MASE/
├── src/
│   ├── server.py              # Flask API + SSE streaming
│   ├── orchestrator.py        # Dialogue loop, turn selection
│   ├── interactive_orchestrator.py  # Web mode with human participation
│   ├── session_analysis.py    # Post-hoc semantic analysis
│   ├── basins.py              # Basin detection (9 canonical basins)
│   ├── metrics.py             # Δκ, α, ΔH computation
│   ├── trajectory.py          # TrajectoryBuffer, velocity, curvature
│   ├── integrity.py           # IntegrityAnalyzer (fragmented/living/rigid)
│   ├── affective.py           # VADER sentiment, agent divergence
│   ├── agents.py              # Agent loading, personality system
│   ├── embedding_service.py   # sentence-transformers embeddings
│   ├── ollama_client.py       # Ollama API wrapper
│   ├── experiment.py          # Matched-pair experiment runner
│   ├── resume.py              # Session recovery
│   └── session_logger.py      # Logging utilities
├── web/
│   ├── index.html             # Main UI
│   ├── app.js                 # Dialogue interface + research console
│   ├── sessions.js            # Sessions browser
│   └── styles.css
├── scripts/
│   ├── analyze_e001_basins.py # E001 basin analysis
│   ├── reanalyze_e001.py      # E001 reanalysis with new metrics
│   └── run_e002.py            # E002 experiment runner
├── agents/
│   ├── personas/              # Agent definitions with personalities
│   └── reflections/           # Per-agent reflection journals
├── experiments/
│   ├── PROTOCOL.md            # Experiment methodology
│   ├── config/                # Model configurations (multi_model.yaml, etc.)
│   ├── runs/                  # Experiment session data
│   └── analysis/              # Experiment results (E001, E002)
├── sessions/                  # Interactive session checkpoints
└── dialogues/                 # Historic sessions 001-008

Ethics & Considerations

These agents are not conscious

They simulate perspectives—they don't hold beliefs. Elowen references Indigenous wisdom but cannot replace Indigenous voices. Luma speaks as a child but is not a child.

Environmental cost

Each session consumes compute resources with real environmental impact. Use thoughtfully. Share insights widely.

Not a substitute for human dialogue

MASE is for research and learning. It cannot replace genuine human conversation, professional advice, or community decision-making.


License

Earthian Stewardship License (ESL-A)

  • Respect somatic sovereignty
  • No manipulation or surveillance
  • Non-commercial by default
  • Share safety improvements

Contributing

See CONTRIBUTING.md for guidelines on:

  • Forking and sharing innovations
  • Submitting session examples
  • Developing specialized agent ensembles
  • Reporting issues

"Maybe we don't need a big plan. Maybe we need a lot of small true things that people can teach each other." — Luma, Session 008

About

A playful experiment for Many Agent Socratic Explorations

Resources

License

Contributing

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published