Skip to main content

YUYAY Intelligence Framework

CI Coverage PyPI version Python versions

A multi-dimensional intelligence framework for evaluating alignment across 12 archetype dimensions — developed for the UN Office of the Future by Mitchell Gold.

pip install yuyay

Quickstart

from yuyay.archetypes import get_archetype_by_name
from yuyay.questionnaire import process_responses
from yuyay.fios import FIOS, FIOSConfig

# Look up an archetype
archetype = get_archetype_by_name("The Seer")
print(archetype.summary())
# → The Seer: Vision, source insight, coherence sensing

# Process questionnaire responses
report = process_responses({
    "1a": "YES",
    "1b": "NO", 
    "2a": "PO",
})
print(report.summary())
# → YES: 1 | NO: 1 | PO: 1 | Total: 3 | Flagged: 2

# Query an LLM with YUYAY context injected
import asyncio

async def main():
    fios = FIOS(FIOSConfig(
        provider="anthropic",
        model="claude-opus-4-6",
        api_key="your-key",
    ))
    result = await fios.query("What is the highest purpose of technology?")
    print(result.summary())
    # → [anthropic/claude-opus-4-6] Tokens: 850 | Latency: 1240ms | Coherence: 80/100 | Cost: $0.002400

asyncio.run(main())

Modules

Module Purpose
archetypes.py 12 YUYAY archetypes with gifts and shadow aspects
transformers.py 10 transformer questions with lookup functions
wheel.py Co-Creation Wheel — 12 societal sectors
questionnaire.py YES/NO/PO response processor with scoring
po.py Edward de Bono PO lateral thinking logic
fios.py LLM orchestration — OpenAI, Anthropic, Google
exceptions.py Custom exception hierarchy
config.py Environment-based configuration

FIOS — LLM Orchestration

FIOS (Foundational Intelligent OS) injects the full YUYAY framework as system context into any LLM query and evaluates the response for coherence.

from yuyay.fios import FIOS, FIOSConfig

# Query all three providers concurrently
fios = FIOS(FIOSConfig(provider="mock", model="mock-model"))
results = await fios.query_all_providers(
    "What is wisdom?",
    configs=[
        FIOSConfig(provider="anthropic", model="claude-opus-4-6", api_key="..."),
        FIOSConfig(provider="openai", model="gpt-4", api_key="..."),
        FIOSConfig(provider="google", model="gemini-pro", api_key="..."),
    ]
)
for r in results:
    print(r.summary())

Features:

  • Provider adapter pattern — swap providers without changing business logic
  • Automatic YUYAY context injection into every prompt
  • Response coherence scoring against 12 archetype dimensions
  • Token usage tracking and cost estimation per provider
  • Retry logic with exponential backoff
  • Circuit breaker pattern for resilience
  • Concurrent multi-provider queries via asyncio

The 12 Archetypes

The Seer · The Architect · The Bridgebuilder · The Steward · The Navigator · The Maker · The Catalyst · The Harmonizer · The Sage · The Oracle · The Alchemist · The Weaver

The Transformer Questions (10 questions, 12 response fields)

Questions 1 and 2 have sub-parts (a and b), giving 12 total response fields.

Each answerable as YES, NO, or PO (Edward de Bono's lateral thinking operator):

  1. Does the idea serve my highest purpose?
  2. Is it relevant?
  3. Do I have enough information to decide?
  4. Can we involve other stakeholders?
  5. Am I being Wise?
  6. Are Judgments or Bias present?
  7. Have I used compassion and mercy?
  8. Is my heart making the decision on its own?
  9. Does this allow peak performance?
  10. Will something of lasting endurance be created?

Developed by Mitchell Gold — UN Office of the Future
Engineering by Ekansh Singh — Georgia Institute of Technology

Metadata

Release files for yuyay 0.3.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for yuyay 0.3.2
File Size Uploaded Provenance
yuyay-0.3.2.tar.gz 23.7 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for yuyay 0.3.2
File Interpreter ABI Platform
yuyay-0.3.2-py3-none-any.whl Python 3 none any Details

Total release size: 40.7 kB

Release files / yuyay-0.3.2.tar.gz

Download URL yuyay-0.3.2.tar.gz
Size 23.7 kB
Tags Source
SHA-256 checksum
How to use checksums
0da1e01db77aec7a0588a7c69f9330bc5cbacefa6f9d99e94b6603081738be3a
BLAKE2b-256 checksum
How to use checksums
2e7f58f8c8c54f35482de5ea39661abaaa1fd9705004dcbe538b1f2a43c96866
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.13

Release files / yuyay-0.3.2-py3-none-any.whl

Download URL yuyay-0.3.2-py3-none-any.whl
Size 16.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
36af26ff5b0df3874ba95206f7e6447a1420360ec8f4acf96cf2e24da1bd9ace
BLAKE2b-256 checksum
How to use checksums
9d1e6d7a1829b264e5b71ec64408d733e65c3b8c162abe1d75075283085da03a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.13

Security for yuyay 0.3.2

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page