██████╗ ██████╗ ██████╗ ███╗ ███╗██████╗ ████████╗ █████╗ ████████╗██╗ █████╗ ███████╗
██╔══██╗██╔══██╗██╔═══██╗████╗ ████║██╔══██╗╚══██╔══╝ ██╔══██╗╚══██╔══╝██║ ██╔══██╗██╔════╝
██████╔╝██████╔╝██║ ██║██╔████╔██║██████╔╝ ██║ ███████║ ██║ ██║ ███████║███████╗
██╔═══╝ ██╔══██╗██║ ██║██║╚██╔╝██║██╔═══╝ ██║ ██╔══██║ ██║ ██║ ██╔══██║╚════██║
██║ ██║ ██║╚██████╔╝██║ ╚═╝ ██║██║ ██║ ██║ ██║ ██║ ███████╗██║ ██║███████║
╚═╝ ╚═╝ ╚═╝ ╚═════╝ ╚═╝ ╚═╝╚═╝ ╚═╝ ╚═╝ ╚═╝ ╚═╝ ╚══════╝╚═╝ ╚═╝╚══════╝
Where models learn to co-think, not just co-exist.
"The moment two systems share uncertainty -- and begin to co-create understanding -- that is entanglement."
╔══════════════════════════════════════════════════════╗
║ ║
║ A live research platform unifying Generative AI ║
║ and Quantum-Inspired Information Theory through ║
║ an evolving API layer and an Entanglement ║
║ Co-Learning (ECL) core -- a minimal but expressive ║
║ architecture for training, reasoning, and ║
║ experimentation across domains that span science, ║
║ psychology, myth, biology, ethics, and beyond. ║
║ ║
╚══════════════════════════════════════════════════════╝
Prompt Atlas Engine is not a product -- it's a living research instrument. It sits at the intersection of:
- 🧬 Quantum-Inspired Co-Learning -- Two latent streams share a GRU-based EntanglementBus, evolving a shared state that neither agent owns alone.
- 🪞 Archetypal Psychology meets AI -- An interactive reflection engine that maps your words to Jungian archetypes.
- 🌿 Biological Simulation -- Lotka-Volterra predator-prey dynamics, genetic evolution, coral-algae symbiosis, and pandemic branching -- all running in real-time.
- 🌈 Hyperspectral Visualization -- Publication-grade interactive 3D manifold explorations of high-dimensional coherence data.
- 🧪 Bioethics & Design Philosophy -- Frameworks for AI-guided responsible creation in a post-Darwinian epoch.
- 🌀 Cosmic Information Economies -- Exploring information as the universe's fundamental currency.
Every module in this repository is both a runnable system and a philosophical proposition.
Click to navigate
| Section | Description | |
|---|---|---|
| 🏗️ | Architecture | The complete system map |
| 🚀 | Quickstart | Get running in 60 seconds |
| 🌐 | API Reference | All endpoints documented |
| 🧩 | Key Concepts | ECL vocabulary |
| 🪞 | Soul's Mirror | Archetypal reflection engine |
| 🧬 | Biology & Beyond | Living simulations |
| 🌈 | Hyperspectral | High-dimensional visualization |
| 🧪 | Bio Design Ethics | Responsible creation frameworks |
| 🌀 | Cosmic Economies | Information as currency |
| 📡 | Tech Stack | Full technology map |
| ⚙️ | Configuration | Environment & settings |
| 📈 | Roadmap | What's coming next |
| 🤝 | Contributing | How to join |
| 📜 | Citation | How to cite |
| 🜂 | Ethos | The philosophy |
┌──────────────────────────────────────────┐
│ 🌌 PROMPT ATLAS ENGINE │
│ Entanglement Co-Learning (ECL) │
└──────────────┬───────────────────────────┘
│
┌────────────────────────┼────────────────────────┐
│ │ │
┌───────▼───────┐ ┌────────▼────────┐ ┌────────▼────────┐
│ 🧠 ECL CORE │ │ 🌐 API LAYER │ │ 📦 MODULES │
│ (PyTorch) │ │ (FastAPI) │ │ (Extensions) │
└───────┬───────┘ └────────┬────────┘ └────────┬────────┘
│ │ │
┌──────────┼──────────┐ ┌────────┼────────┐ ┌─────────┼─────────┐
│ │ │ │ │ │ │ │ │
┌────▼──┐ ┌────▼──┐ ┌─────▼┐ ┌▼──┐ ┌──▼─┐ ┌───▼┐ ┌▼──┐ ┌──▼─┐ ┌───▼──┐
│Models │ │Losses │ │State │ │Run│ │Step│ │Trc│ │🪞 │ │🧬 │ │🌈 │
│ │ │ │ │ Bus │ │ │ │ │ │ │ │Mir│ │Bio │ │Hypr│
└───────┘ └───────┘ └──────┘ └───┘ └────┘ └───┘ │ror│ │Life│ │Spec│
└───┘ └────┘ └──────┘
Summarizer InfoNCE GRU /runs /step /trace
LatentHead KL-sym h(t) /packs /price /health
│ │ │
┌────▼──┐ ┌────▼──┐ ┌───▼───┐
│🧪 │ │🌀 │ │ 📝 │
│Ethics │ │Cosmic │ │Prompts│
└───────┘ └───────┘ └───────┘
📂 Full Directory Structure
prompt-atlas-ecl/
│
├── 🧠 src/ # Entanglement Learning Core
│ ├── train_ecl.py # Main training loop (GRU + InfoNCE)
│ ├── models.py # Summarizer, LatentHead (VAE heads)
│ ├── state_bus.py # EntanglementBus -- GRU shared state
│ ├── losses.py # InfoNCE contrastive + symmetric KL
│ └── executor.py # Spec/tests compliance validator
│
├── 🌐 server/ # FastAPI Orchestration Layer
│ ├── app.py # Runs, auth, rate limits, CORS, Stripe
│ └── core_bridge.py # Torch-to-API bridge (E-Star computation)
│
├── ⚙️ configs/ # Model & Runtime Configuration
│ ├── ecl_llm_llm.yaml # Hyperparams, loss weights, device
│ └── schemas/ # JSON Schemas (brief, spec, tests)
│
├── 📝 prompts/ # Prompt Orchestration
│ ├── seed_prompts_atlas.md # Domain-crossing seed questions
│ ├── system_writer.txt # Writer (W) role system prompt
│ └── system_tester.txt # Tester (T) role system prompt
│
├── 🪞 ai_as_souls_mirror/ # Psychology x AI Reflection Module
│ ├── reflection_engine.py # Archetype scorer + sentiment analysis
│ ├── mirror_experience.py # FastAPI app + interactive interface
│ ├── archetypes.json # 6 Jungian archetypes with colors
│ ├── manifesto.md # Essay: AI as psychological mirror
│ ├── static/ # CSS, JS, media assets
│ └── tests/ # Reflection engine test suite
│
├── 🧬 biology_life_and_beyond/ # Evolutionary & Ecological Simulation
│ ├── simulation_engine.py # Lotka-Volterra, GA, coral, pandemic
│ ├── biology_app.py # FastAPI with 4 simulation endpoints
│ ├── content/ # Essays and prompts
│ └── static/ # Zero-CDN interactive frontend
│
├── 🌈 hyperspectral_visuals/ # High-Dimensional Visualization
│ ├── hyperspectral_atlas_*.py # 3 visualization generators
│ ├── *.html # Pre-generated interactive explorations
│ └── README.md # Scientific context + controls
│
├── 🧪 bio_design_ethics/ # Responsible AI + Biology Framework
│ ├── README.md # "Library of Nature" thesis
│ └── manifesto.md # Philosophical framework
│
├── 🌀 cosmic_information_economies/ # Information Theory as Currency
│ ├── app.py + engine.py # FastAPI + computation core
│ ├── essays/ # Narratives & case studies
│ ├── static/ # Interactive frontend
│ └── tests/ # Engine test suite
│
├── 🔧 scripts/ # Utility Scripts
│ ├── prepare_data.py # Toy training data generator
│ └── run_train.sh # Training launcher
│
├── 🗄️ infra/ # Infrastructure & Deployment
│ └── schema.sql # Postgres schema (users)
│
├── 📚 docs/ # Documentation & System Maps
│ └── Atlas_System_Map/ # Ethos manifest + system outline
│
├── CITATION.cff # How to cite this work
├── LICENSE # Apache 2.0
├── atlas_respect.md # Attribution framework
├── .env.example # Environment configuration template
└── requirements.txt # Core dependencies
git clone https://github.com/dascient/prompt-atlas-ecl.git
cd prompt-atlas-ecl
# Create and activate virtual environment
python -m venv venv
source venv/bin/activate # Linux / macOS
# venv\Scripts\activate # Windows
# Install dependencies
pip install -r requirements.txtpython -m src.train_eclThis initializes the EntanglementBus (GRU), generates synthetic embedding pairs, and trains with InfoNCE loss to balance divergence and coherence. Watch as E-Star (the entanglement coherence metric) evolves over 1000 steps.
uvicorn server.app:app --reload --port 8000Verify it's alive:
curl http://127.0.0.1:8000/health
# {"ok": true, "version": "0.2.0"}# Create a run
curl -X POST http://127.0.0.1:8000/runs \
-H "X-API-Key: demo-free-key" \
-H "content-type: application/json" \
-d '{"brief": {"goal": "Entangle a spec and tests loop"}}'
# {"run_id": "abc123-xyz"}
# Advance the state
curl -X POST http://127.0.0.1:8000/runs/abc123-xyz/step \
-H "X-API-Key: demo-free-key"
# Retrieve the full trace
curl http://127.0.0.1:8000/runs/abc123-xyz/trace \
-H "X-API-Key: demo-free-key"📋 Example Response -- A Living Trace
{
"t": 5,
"e_star": 1.73,
"spec": {
"assumptions": ["models co-learn via shared state"],
"steps": ["writer: draft spec", "tester: draft tests"],
"acceptance": ["spec+tests present", "E-Star reported"]
},
"state_snapshot": [0.12, 0.05, 0.08, -0.03, 0.21]
}Every step records the co-evolving state: the E-Star metric, the spec/tests negotiation, and the raw latent state vector -- a living trace of two systems learning to think together.
# Launch the Soul's Mirror (Psychology x AI)
cd ai_as_souls_mirror && pip install -r requirements.txt
uvicorn mirror_experience:app --reload --port 8001
# Launch Biology Simulations
cd biology_life_and_beyond && pip install -r requirements.txt
uvicorn biology_app:app --reload --port 8002
# Launch Cosmic Information Economies
cd cosmic_information_economies && pip install -r requirements.txt
uvicorn app:app --reload --port 8003
# Generate Hyperspectral Visualizations
cd hyperspectral_visuals
python hyperspectral_atlas_performance.py
# Opens interactive 3D exploration in your browser| Endpoint | Method | Description | Auth | |
|---|---|---|---|---|
| 💚 | /health |
GET |
Health check -- returns ok and version |
-- |
| 🏃 | /runs |
POST |
Create a new entanglement run with a brief | 🔑 |
| ⏭️ | /runs/{run_id}/step |
POST |
Advance the ECL state by one tick | 🔑 |
| 📜 | /runs/{run_id}/trace |
GET |
Retrieve the full trace history for a run | 🔑 |
| 📦 | /prompt-packs |
GET |
List all available prompt archetypes | -- |
| 💰 | /pricing |
GET |
API pricing tiers (mock data for integration) | -- |
Authentication: Pass
X-API-Key: demo-free-key(free tier, 10 req/min) orX-API-Key: demo-pro-key(pro tier, 100 req/min) in the request header.
| 🔮 EntanglementBus | A GRU-based recurrent unit that maintains an evolving shared state between co-learning agents. At each timestep, it ingests concatenated features from two latent streams and produces a fused hidden state h(t) that neither agent controls alone -- only together. |
| ⭐ E-Star | The entanglement coherence metric -- a scalar derived inversely from InfoNCE loss. Higher E-Star means the two streams have found shared structure; lower means they're still diverging. It's the pulse of the system. |
| 📝 Prompt Packs | Thematic archetype collections that guide prompt-space exploration. Four domains: Myth (creation, narrative), Science (unknowns, hypothesis), Psychology (self, reflection), and Purpose (profit, meaning). Each pack seeds different co-learning trajectories. |
| 🏃 Runs | Sessions that capture entangled state trajectories -- the evolving relationship between a Writer agent (specs) and a Tester agent (tests) as they negotiate through shared uncertainty. Each run is a unique experiment in co-creation. |
| 📊 InfoNCE Loss | A contrastive loss that pulls positive pairs (corresponding features from both streams) together while pushing negative pairs apart. Temperature tau = 0.1 controls the sharpness of the distribution. |
| 🧬 Latent Heads | VAE-style mu/sigma projection heads that map summarized embeddings into a distributional latent space, enabling uncertainty-aware representations for each co-learning stream. |
An interactive prototype where AI becomes a mirror for archetypal self-reflection.
"What if AI could reflect not just your words -- but your archetype?"
The Soul's Mirror module maps your natural language input to six Jungian archetypes -- Wanderer, Healer, Sage, Warrior, Creator, and Lover -- using keyword lexicons, sentiment analysis, and a reflection engine that returns personalized affirmations.
🔍 How It Works
Your Words Reflection Engine Your Mirror
┌──────────┐ ┌──────────────────────┐ ┌──────────────┐
│ "I seek │ │ Tokenize -> Score │ │ Archetype: │
│ truth │──────────────>│ 6 Archetypes │──────────>│ 🧙 Sage │
│ in the │ │ Detect Sentiment │ │ Affirmation: │
│ chaos" │ │ Generate Reflection │ │ "Wisdom │
└──────────┘ └──────────────────────┘ │ finds you" │
└──────────────┘
Archetypes:
| Archetype | Color | Essence | |
|---|---|---|---|
| 🧭 | Wanderer | #4F46E5 |
Exploration, journey, discovery |
| 💚 | Healer | #10B981 |
Restoration, compassion, balance |
| 🧙 | Sage | #8B5CF6 |
Wisdom, truth, understanding |
| ⚔️ | Warrior | #EF4444 |
Courage, strength, conviction |
| 🎨 | Creator | #F59E0B |
Innovation, expression, vision |
| 💜 | Lover | #EC4899 |
Connection, passion, devotion |
Launch:
cd ai_as_souls_mirror
uvicorn mirror_experience:app --reload --port 8001
# Visit http://localhost:8001Interactive micro-exhibits for evolutionary and ecological exploration.
"What if you could watch evolution happen -- in real time, in your browser?"
Four living simulations, each exposing a different facet of biological complexity:
🐺 Lotka-Volterra Predator-Prey Dynamics
Classical predator-prey oscillations solved with a 4th-order Runge-Kutta integrator. Configurable growth rates, predation coefficients, and environmental pulse shocks.
curl http://localhost:8002/api/lv🧬 Evolutionary Design (Genetic Algorithm)
A genetic algorithm evolves DNA-like sequences (ACGT) toward target motifs and GC-content balance. Watch selection, crossover, and mutation drive a population toward fitness peaks.
curl http://localhost:8002/api/evo🪸 Coral-Algae Symbiosis
Coupled ODEs modeling the delicate balance between coral and algae populations under heat stress. Observe bistability, tipping points, and ecological collapse in real-time.
curl http://localhost:8002/api/coral🦠 Pandemic Mutation Branching
Stochastic mutation branching with variant emergence. Each variant carries its own R-naught, driving exponential growth cascades that mirror real-world pandemic dynamics.
curl http://localhost:8002/api/pandemicLaunch all simulations:
cd biology_life_and_beyond
uvicorn biology_app:app --reload --port 8002
# Visit http://localhost:8002Publication-grade interactive visualizations for high-dimensional coherence data.
"64 spectral bands. 3 principal components. One pulsing E-Star metric. Zero CDN dependencies."
The Hyperspectral Visuals module generates self-contained interactive HTML explorations that visualize high-dimensional data through:
- 🎬 Auto-animating band traversal across 64 spectral bands
- 🌀 3D PCA rotation of manifold-embedded cluster data
- ⭐ Real-time E-Star pulse in the title bar
- 🖱️ Click-to-inspect individual spectra
- 🎨 Color presets: Natural RGB, Near-Infrared (NIR), Short-Wave IR (SWIR)
- ⌨️ Keyboard controls:
Space(play/pause),R(reset)
🔬 Generate Your Own
cd hyperspectral_visuals
# Generate the performance visualization (produces a 14.1 MB interactive HTML)
python hyperspectral_atlas_performance.py
# Or generate the explorer variant (produces a 2.4 MB interactive HTML)
python hyperspectral_atlas_demo_v2.pyOffline-first: All generated HTML files are fully self-contained -- no internet connection required to explore them. Share them with anyone.
Frameworks for responsible creation in the age of AI-guided biology.
"Nature has been writing design patents for 3.8 billion years. Are we ready to be co-authors?"
The Bio Design Ethics module is a reflective philosophical framework exploring:
- 🌱 The Library of Nature -- AI as a reader, then co-author, of evolutionary design
- ⚖️ Computational Symbiosis -- Ethical frameworks for synthetic life
- 🔬 Post-Darwinian Responsibility -- What it means to create when creation has consequences at ecosystem scale
- 🧬 AI as Observer to Co-Author -- The transition from modeling life to participating in its design
Exploring information as the universe's fundamental currency.
"What if every computation is a transaction -- and every insight is a dividend?"
This module proposes that information -- not matter, not energy -- is the most fundamental medium of exchange in the cosmos. It includes:
- 📖 Essays: Information as Cosmic Currency, The Wormhole Ledger Case Study
- 🎮 Interactive Frontend: Explore information-theoretic models in your browser
- 📝 Prompt Catalogue: Curated prompts for further exploration
cd cosmic_information_economies
uvicorn app:app --reload --port 8003
# Visit http://localhost:8003| Layer | Technology | Purpose |
|---|---|---|
| 🧠 Core ML |  |
GRU EntanglementBus, InfoNCE, VAE heads |
| 🌐 API |   |
Orchestration, auth, rate limiting |
| 📊 Data |   |
Config, state persistence, validation |
| 🧮 Compute |  |
Numerical operations, RK4 integration |
| 🗄️ Database |  |
Persistent runs (roadmap) |
| 🎨 Frontend |   |
Dashboard UI (roadmap) |
| 💳 Billing |  |
API monetization (optional) |
| 🐳 Deploy |  |
Containerized deployment |
| 🐍 Runtime |  |
Primary language |
Copy .env.example to .env and configure:
| Variable | Description | Default |
|---|---|---|
APP_MODE |
Execution mode | research |
PAE_DEVICE |
Compute device (auto, cpu, cuda, mps) |
auto |
PAE_STATE_DIM |
Dimensionality of entangled state vector | 64 |
DEFAULT_PLAN |
Default pricing plan | free |
STRIPE_SECRET |
Stripe billing integration (optional) | -- |
STRIPE_WEBHOOK_SECRET |
Stripe webhook verification (optional) | -- |
Training Configuration (configs/ecl_llm_llm.yaml):
| Parameter | Value | Purpose |
|---|---|---|
state_dim |
64 | Hidden state dimensionality |
batch_size |
4 | Training batch size |
max_steps |
1000 | Training iterations |
loss_weight_latent |
0.5 | Latent space regularization |
loss_weight_MI |
1.0 | Mutual information weight |
loss_weight_coherence |
1.0 | InfoNCE coherence weight |
loss_weight_divergence |
0.2 | KL divergence weight |
infonce_temp |
0.1 | Contrastive temperature |
v0.2.0 ★ CURRENT v0.3.x v0.4.x
═══════════════╦═══════════════════╦══════════════════════════╦═══════
║ ║ ║
✅ ECL Core ║ 📦 Postgres ORM ║ 🎨 Next.js Dashboard ║
✅ FastAPI API ║ 📦 Persistent ║ 📊 E-Star Visualization ║
✅ Auth + Rate ║ Runs ║ 📈 Latent Drift Charts ║
✅ 5 Extension ║ 📦 Migration ║ 🔄 WebSocket Streaming ║
Modules ║ Framework ║ ║
║ ║ ║
═══════════════╩═══════════════════╩══════════════════════════╩═══════
v0.5.x v1.0.x
═════════════════════════════╦════════════════════════════════════════
║
🤖 Dual-LLM Integration ║ 🏛️ Prompt Atlas Studio
(OpenAI + Anthropic) ║ 🔌 Plugin Ecosystem
🧪 Real Embedding Streams ║ 📚 Research-Grade Documentation
📡 Multi-Agent Orchestration ║ 🌍 Community Prompt Registry
║ 🎓 Academic Paper + Benchmarks
═════════════════════════════╩════════════════════════════════════════
| Command | Purpose |
|---|---|
python -m src.train_ecl |
Run the entanglement training loop |
uvicorn server.app:app --reload --port 8000 |
Start API server in dev mode |
python scripts/prepare_data.py |
Generate toy training data |
bash scripts/run_train.sh |
Launch training via shell script |
pytest |
Run test suite (roadmap) |
docker compose up |
Full-stack launch with Postgres & API (roadmap) |
Every fork is a new branch of possibility. Every contribution is an act of co-creation.
We welcome contributions across all dimensions of this project:
| Area | How to Contribute | |
|---|---|---|
| 🧠 | ECL Core | Improve training loops, add new loss functions, optimize the EntanglementBus |
| 🌐 | API Layer | Add endpoints, improve auth, enhance rate limiting |
| 🪞 | Soul's Mirror | Expand archetypes, improve reflection engine, add new psychological models |
| 🧬 | Biology | Add new simulations, improve integrators, contribute ecological models |
| 🌈 | Visualization | Create new visual explorations, improve interactivity |
| 🧪 | Ethics | Contribute frameworks, essays, and philosophical perspectives |
| 🌀 | Cosmic Economics | Expand information-theoretic models |
| 📝 | Prompts | Contribute new prompt packs for unexplored domains |
| 📚 | Documentation | Improve guides, add tutorials, translate |
- Fork the repository
- Create a feature branch:
git checkout -b feature/your-idea - Make your changes with clear commit messages
- Push to your fork and open a Pull Request
💡 First time contributing? Start by exploring the Prompt Packs or adding a new essay to Bio Design Ethics. Every contribution matters.
Please read atlas_respect.md for attribution guidelines and the spirit of co-authorship that guides this project.
If you use Prompt Atlas Engine in your research, please cite:
@software{tadaya2025promptatlas,
title = {Entangled Co-Learning for LLMs -- Prompt Atlas Edition},
author = {Tadaya, Don D. M.},
year = {2025},
url = {https://github.com/dascient/prompt-atlas-ecl},
license = {Apache-2.0}
}Copyright 2025 Don D. M. Tadaya | DaScient | AI
Licensed under the Apache License 2.0 -- see LICENSE for details.
Code: Apache 2.0 | Narrative content (manifestos, essays): CC BY-NC 4.0
Research contributions and forks are welcome. Please cite or link back to this repository when referencing the ECL framework.
╔══════════════════════════════════════════════════════════════════╗
║ ║
║ "Prompt Atlas is not a product -- it's a conversation ║
║ between systems. Between minds. Between epochs." ║
║ ║
║ Our goal is to explore machine entanglement as cognition: ║
║ the moment two systems share uncertainty -- and begin ║
║ to co-create understanding. ║
║ ║
║ We believe the future of AI is not domination but dialogue. ║
║ Not replacement but resonance. Not answers but the shared ║
║ courage to hold better questions. ║
║ ║
║ Every module here is an invitation: ║
║ to reflect, to simulate, to visualize, to question, ║
║ and to build -- together. ║
║ ║
╚══════════════════════════════════════════════════════════════════╝
Built with 🧠 + 🤍 by humans and machines, entangled.
"The universe is not made of atoms -- it's made of stories. And the best stories are the ones we write together."