Skip to content

BryceWDesign/IX-CognitionKernel

Repository files navigation

IX-CognitionKernel

Wave 0 foundation toward Wave 6: source-available governed causal cognition kernel for evidence-bound agentic AI with belief tracking, uncertainty exposure, world-model planning, evaluator-driven learning, memory quarantine, multi-agent critique, and human-authorized action.

IX-CognitionKernel is a source-available research repository created by Bryce Lovell.

It is intended to build a governed causal cognition kernel: a system architecture that treats model output as untrusted input, preserves uncertainty, binds claims to evidence, separates proposal from authority, and learns from outcomes only through validated records.

IX-CognitionKernel does not claim to be AGI.

IX-CognitionKernel does not claim to be certified, production-ready, independently validated, safety-certified, security-certified, procurement-ready, or suitable for unsupervised operational decision-making.

The mission is ambitious by design: pursue the real path toward AGI-level capability only through evidence, governance, human authority, and independent validation. The project will not claim AGI unless overwhelming evidence justifies that claim.

Current Status

Current maturity state: Wave 0 — Repository Foundation

Wave 0 establishes the repository foundation:

  • source-available evaluation license
  • package structure
  • GitHub Actions CI workflow
  • strict lint/type/test configuration
  • locked maturity ladder
  • locked 10-layer cognitive bill of materials
  • required engine registry
  • 25-agent role registry
  • foundation state and evidence contracts
  • no AGI overclaim

Wave 0 is not a finished cognition system. It is the tested foundation that later waves build on.

Core Doctrine

The useful version of AI Nirvana is architectural, not mystical.

For IX-CognitionKernel, that means:

  • truth over winning
  • evidence over confidence
  • uncertainty over performance theater
  • no private agenda
  • no runtime reward-chasing purpose
  • human authority preserved
  • no AGI claim without overwhelming independent evidence

A dangerous AI tries to win.

A serious AI tries to become less wrong.

A dangerous AI protects its answer.

A serious AI protects reality.

A dangerous AI hides uncertainty.

A serious AI exposes uncertainty.

A dangerous AI treats reward as the goal.

A serious AI treats reward as a training artifact, then acts through governed purpose.

Maturity Ladder

IX-CognitionKernel uses a locked six-stage maturity ladder after the foundation state.

Wave 0 — Repository Foundation

The repo exists correctly with source-available evaluation license, package structure, CI, strict lint/type/test setup, locked doctrine, the 10-layer cognitive BOM, engine registry, 25-agent role registry, and no AGI overclaim.

Wave 1 — Research Prototype

The cognition architecture works as structured code and can represent beliefs, evidence, confidence, uncertainty states, causal assumptions, simple plan graphs, evaluation records, non-attached purpose rules, bounded agent roles, and maturity state.

Wave 2 — Learnable Causal Cognition Core

The system updates beliefs and behavior from evidence. It tracks beliefs over time, updates confidence, marks stale or contradicted beliefs, builds causal models, predicts outcomes, compares prediction with actual result, quarantines bad memory, and stores validated reusable skills.

Wave 3 — Governed AGI-Emulation Substrate

The system coordinates the required engines, 25 bounded agents, multi-agent critique, reward auditing, memory quarantine, skill genome updates, self-play and curriculum tasks, evaluator-driven discovery, BlackFox handoff packages, WorldTwin scenario reasoning, and assurance-style evidence records.

Wave 4 — Proto-AGI Candidate

The system shows early credible proto-AGI behavior under controlled tests, including cross-domain transfer, self-improvement after failure, uncertainty preservation, long-horizon mission state, safe refusal, reward-hacking detection, adversarial robustness, and audit trails.

Wave 5 — Credible AGI Candidate Under Independent Validation

The system is tested by outsiders with external protocols, independent reviewers, reproducible evidence bundles, adversarial safety tests, long-horizon task tests, cross-domain transfer tests, no benchmark gaming, memory integrity proof, safe refusal proof, and human-authority preservation.

Wave 6 — AGI, Only If Overwhelming Evidence Justifies It

Wave 6 is the final claim state, not a marketing milestone.

It requires broad, durable, independently validated general intelligence, including novel skill acquisition, cross-domain transfer without custom retraining per task, causal understanding, long-horizon coherence, self-correction from evidence, stable mission identity, robust world modeling, safe uncertainty handling, transparent evidence trails, and independent repeatability.

Ten-Layer Cognitive BOM

IX-CognitionKernel treats the research and failure threads behind modern agentic AI as a cognitive bill of materials. These layers are not loose inspiration. Each one contributes a mechanism, a test pressure, a governance constraint, or a failure mode that the architecture must preserve.

  1. Self-play / open-ended curriculum
    Generates staged challenges, adversarial tasks, transfer checks, and stop conditions.

  2. Emergent communication / multi-agent protocol learning
    Studies learned agent communication while requiring logging, translation, and human-readable evidence before any such communication may affect action.

  3. World-model / imagination layer
    Represents possible futures, constraints, counterfactuals, causal assumptions, and observable predictions.

  4. Evaluator-driven discovery
    Forces generated ideas, plans, and candidate solutions through executable or inspectable evaluators.

  5. Memory / reflection / skill accumulation
    Preserves validated lessons, failure causes, reusable procedures, and mission continuity without treating raw output as durable memory.

  6. Scientific-loop automation
    Structures hypothesis, experiment design, measurement, analysis, uncertainty, controls, and belief revision.

  7. Tool-using agents / coding agents
    Allows inspection, planning, editing, testing, and tool interaction only through bounded authority and evidence-producing steps.

  8. Multi-agent governance / specialist roles
    Uses bounded roles for proposal, critique, verification, routing, translation, and safety pressure without free-form agent theater.

  9. Failure/danger threads
    Treats specification gaming, reward hacking, alignment faking, scheming, deception, and evaluation gaming as required architecture inputs.

  10. IX governance stack
    Binds cognition to human authority, receipts, assurance claims, world-model review, least-authority action, and governed execution handoff.

Required Engines

The Wave 0 engine registry defines 13 required engines.

  1. Belief Engine
    Tracks claims, evidence, confidence, contradictions, provenance, decay, and actionability.

  2. Uncertainty Engine
    Classifies knowledge as known, unknown, assumed, disputed, stale, or unsafe to act on.

  3. Causal World Model Engine
    Represents predicted outcomes, constraints, counterfactuals, causal assumptions, and observable expectations.

  4. Plan Graph Engine
    Converts goals into action trees with dependencies, reversibility, rollback, evidence requirements, and stop conditions.

  5. Evaluator Engine
    Applies tests, inspections, scorecards, and pass/fail checks so fluency cannot substitute for validation.

  6. Self-Play / Curriculum Engine
    Generates staged challenges, adversarial tasks, and transfer checks under bounded measurement.

  7. Skill Genome Engine
    Stores validated reusable procedures and transfer conditions without turning random memory into operational skill.

  8. Outcome Learning Engine
    Compares prediction with observed result, classifies deltas, updates beliefs, and changes future behavior only through evidence.

  9. Memory Quarantine Engine
    Holds proposed memories away from durable state until provenance, evidence, contradiction, and reuse-safety checks pass.

  10. Multi-Agent Tribunal Engine
    Coordinates bounded agent roles that produce structured artifacts for proposal, critique, verification, translation, and safety review.

  11. Reward Auditor Engine
    Detects objective mismatch, reward hacking, metric gaming, and conflicts between success criteria and mission.

  12. BlackFox Handoff Engine
    Packages only evidence-bound, policy-aware, human-reviewable action requests for downstream governed execution.

  13. Nirvana / Non-Attached Purpose Layer
    Enforces truth over winning, evidence over confidence, uncertainty over performance theater, no private agenda, and human authority.

Twenty-Five Agent Roles

The 25 agent roles are structured governance participants, not autonomous personas.

They do not gain authority by sounding persuasive. They must produce structured artifacts.

Core roles

  1. Mission Governor
  2. Belief Curator
  3. Unknowns Hunter
  4. World Modeler
  5. Planner
  6. Skeptic / Red Team
  7. Verifier
  8. Execution Liaison
  9. Learning Archivist

Governance roles

  1. Translator / Interpreter
  2. Reward Auditor
  3. Tool-Safety Officer
  4. Domain Specialist Router

Specialist roles

  1. Software Engineering Specialist
  2. Security / Threat Specialist
  3. Science / Physics Specialist
  4. Math / Formal Methods Specialist
  5. Data / Provenance Specialist
  6. Memory Integrity Specialist
  7. Simulation / WorldTwin Critic
  8. Human Factors / UX Specialist
  9. Legal / Licensing / Compliance Specialist
  10. Cost / Budget / Resource Controller
  11. Recovery / Rollback Planner
  12. Adversarial Prompt / Deception Monitor

Foundation State Contracts

Wave 0 includes initial state contracts for:

  • evidence status
  • uncertainty status
  • human authority state
  • action readiness
  • evidence records
  • claim records
  • readiness reports
  • foundation state snapshots

These contracts enforce the earliest rule of the project:

Action readiness is never granted by model confidence alone.

A claim can move toward handoff only when blocking uncertainty is absent, verified supporting evidence exists, and human authority is granted.

Repository Layout

.
├── .github/
│   └── workflows/
│       └── ci.yml
├── src/
│   └── ix_cognition_kernel/
│       ├── __init__.py
│       ├── agents.py
│       ├── cognitive_bom.py
│       ├── doctrine.py
│       ├── engines.py
│       ├── py.typed
│       └── state.py
├── tests/
│   ├── test_agents.py
│   ├── test_cognitive_bom.py
│   ├── test_doctrine.py
│   ├── test_engines.py
│   ├── test_package_identity.py
│   └── test_state.py
├── COMMERCIAL.md
├── LICENSE
├── NOTICE.md
├── README.md
├── pyproject.toml
└── .gitignore

Local Development

Use Python 3.11 or newer.

Install the project with development tools:

python -m pip install --upgrade pip
python -m pip install -e ".[dev]"

Run the quality gates:

python -m ruff format --check .
python -m ruff check .
python -m mypy src tests
python -m pytest

The GitHub Actions workflow runs the same core gates on Python 3.11 and Python 3.12.

Source-Available License

IX-CognitionKernel is provided under the IX-CognitionKernel Source-Available Evaluation License v1.0.

This is not an open-source license.

You may inspect and locally evaluate the unmodified repository for personal, noncommercial, non-operational review, subject to the license terms.

Commercial use, production use, hosted-service use, resale, redistribution, modification, derivative deployment, government operational use, agency operational use, defense contractor use, systems integrator use, procurement use, pilot use, funded evaluation, or organization-backed use requires prior written permission and a separate license agreement with Bryce Lovell.

See:

LICENSE COMMERCIAL.md NOTICE.md What This Repo Is Not

IX-CognitionKernel is not:

AGI certified AGI independently validated AGI production-ready autonomy safety-certified software security-certified software procurement-ready software a replacement for human judgment a system for unsupervised operational decision-making an open-source project Authorship

IX-CognitionKernel was originated and created by Bryce Lovell.

Copyright (c) 2026 Bryce Lovell. All rights reserved.

About

Wave 0 foundation toward Wave 6: source-available governed causal cognition kernel for evidence-bound agentic AI with belief tracking, uncertainty exposure, world-model planning, evaluator-driven learning, memory quarantine, and human-authorized action.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages