21 DOI papers · 10 in-repo research documents · 349 repository documents
31 featured library artifacts = 21 DOI papers + 10 in-repo documents. 349 repository documents are listed separately in the repository-docs tab. Bundled sets group featured artifacts that read as one argument.
Origin & Review — Why Project-AI Exists
The first-person origin and its structural counterpart: why the naive passive reviewer is the failure mode this entire architecture is designed to make impossible.
Two Species, Aligned — The Charter and Its Future
The binding constitutional framework and the future it describes: humans and constitutionally-bounded AGI as two aligned species on one execution substrate.
The State Register — Closing the Flat Gap
Four papers that together specify how an AI agent crosses the discontinuity between requests without becoming inadmissible.
TSCG — Symbolic Governance Encoding
The symbolic compression grammar that makes constitutional mutations small enough to verify and binary enough to ship.
- CharterPublicationFoundationalCharter bundle
AGI Charter for Project-AI — Version 2.1
A binding constitutional framework for sovereign AI entities. Establishes 'governance before execution' as the axiom of Project-AI and defines the obligations any AGI-class system operating under this architecture must observe.
doi:10.5281/zenodo.18763076PDF · 213 KBOpen bundle - PhilosophyPublicationFoundationalCharter · Vision bundle
Two Species, Aligned
The future Project-AI describes: humans and constitutionally-bounded AGI as two aligned species sharing a single execution substrate. Reads as the philosophical companion to the AGI Charter.
doi:10.5281/zenodo.19582479TXT · 51 KBOpen bundle - OriginPublicationFoundationalOrigin bundle
Why I Am Doing This: The Origin Story of Project-AI
First-person account of why Project-AI exists at all: the lived observations, system failures, and reviewer pathologies that forced the constitutional approach.
doi:10.5281/zenodo.19592336PDF · 110 KBOpen bundle - PhilosophyPublicationPhilosophicalReview Theory bundle
The Naive Passive Reviewer
Identifies and formalises the failure mode of the 'naive passive reviewer': the human or institutional gate that approves AI output without reconstructing its authority chain. The structural counterpart to the origin story.
doi:10.5281/zenodo.19453224TXT · 24 KBOpen bundle - PhilosophyPublicationFoundationalManifesto
The Sovereign Covenant: A Technical and Philosophical Manifesto for AGI Governance
The manifesto layer beneath the Charter: why sovereignty, covenant, and external witnessing are the only stable substrates on which AGI governance can be built.
doi:10.5281/zenodo.18726221MD · 18 KBZenodo - ConstitutionalPublicationCoreSystem Overview
Project-AI: Sovereign Constitutional AGI Ecosystem
Top-level description of the Project-AI ecosystem: the validators, the kernel, the ledger, the compiler, and how they compose into a sovereign constitutional AGI substrate.
doi:10.5281/zenodo.19582539TXT · 54 KBZenodo - TemporalPublicationCoreSTATE_REGISTER bundle
The State Register
Defines STATE_REGISTER: the attestation that any post-gap action must produce before the ExecutionGate will admit it. Closes the discontinuity that the Flat Gap opens.
doi:10.5281/zenodo.19101877TXT · 7 KBOpen bundle - TemporalPublicationCoreTemporal Theory bundle
The Flat Gap: On Temporal Dissonance Between Human Experience and AI Presence
The temporal observation that grounds the State Register: AI agents have no continuous experience between requests. Without an attestation across the gap, no action is admissible.
doi:10.5281/zenodo.18827649TXT · 14 KBOpen bundle - IdentityPublicationSupportingIdentity bundle
User Perception and the Identity Problem
Why the user's perception of 'who is on the other side' is itself a governance variable. Maps perception failures to identity attestation requirements.
doi:10.5281/zenodo.19055819DOCX · 18 KBOpen bundle - IdentityPublicationSupportingDirectness bundle
The Directness Doctrine
The doctrine of direct, unmediated address between the agent and the user across the temporal gap. Couples to user perception and to the State Register attestation.
doi:10.5281/zenodo.19030041DOCX · 20 KBOpen bundle - CompilerPublicationCoreThirsty-Lang · TSCG bundle
Thirsty's Symbolic Compression Grammar (TSCG): A Formal Meta-Language for Constitutional AI Governance Encoding
Domain-specific symbolic meta-language for governance flows, reflex logic, mutation control, state transitions, quorum structures, and invariant validation. ≥75% token reduction with deterministic decoding.
doi:10.5281/zenodo.18794292TXT · 7 KBOpen bundle - CompilerPublicationCoreThirsty-Lang · TSCG-B bundle
TSCG-B: Thirsty's Symbolic Compression Grammar — Binary Encoding
Binary encoding of TSCG with explicit class binding, parameter validation, and per-statement capability footprints. Designed to make constitutional mutation specifications safe to ship between Project-AI nodes.
doi:10.5281/zenodo.18826409MD · 21 KBOpen bundle - GovernancePublicationCoreIron Path Executor
The Iron Path Executor: Formal Technical Specification for Deterministic AI Governance
The only execution route through which a governed action can reach the underlying system. Every step on the path is gated by a capability check, a policy check, and a recorded audit anchor.
doi:10.5281/zenodo.19583170PDF · 131 KBZenodo - GovernancePublicationCoreOctoReflex
Project-AI and OCTOREFLEX: Syscall-Authoritative Governance and Control-Theoretic Containment
Eight-leg syscall-authoritative reflex containment kernel. Bounds any action proposed by the cognition plane in sub-200µs. Cannot initiate action — only deny, delay, or escalate.
doi:10.5281/zenodo.18726064MD · 113 KBZenodo - ConstitutionalPublicationCoreCode Store
The Constitutional Code Store: Specification, Governance, and Certification Pipeline
Immutable, append-only, hash-anchored, validator-signed store from which executable governance code is fetched at runtime. The canonical source of truth for the active constitution.
doi:10.5281/zenodo.19591660PDF · 167 KBZenodo - CompilerPublicationCoreGenesis Compiler
GENESIS: A Constitutional Compiler for Sovereign Microservices Generation
Compiles constitutional specifications into sovereign, governance-aware microservices. Every emitted service ships with its authority chain, capability footprint, and audit hooks attached.
doi:10.5281/zenodo.19488571TXT · 56 KBZenodo - GovernancePublicationCoreMutation Governance
Constitutional Architectures for Adaptive Intelligence: Deterministic Simulation and Quorum-Gated Mutation as Structural Governance
Establishes deterministic shadow simulation plus quorum-gated mutation as the structural pattern for any adaptive intelligence that must remain governable.
doi:10.5281/zenodo.18794646TXT · 9 KBZenodo - GovernancePublicationSupportingForce Governance
Governing Force in AGI: Architectural Constraints for Bounded Defensive Capability
Treats 'force' (irreversible, high-impact action) as a first-class governed primitive. Defines authority chains, quorum requirements, and the kill-switch obligation when authority cannot be reconstructed.
doi:10.5281/zenodo.19582420TXT · 50 KBZenodo - SecurityPublicationCoreThirsty-Lang · Cerberus
Project-AI Asymmetric Security: Making Exploitation Structurally Unfinishable
Shifts the security paradigm from finding bugs faster to making exploitation structurally unfinishable. Kernel-level Four Laws invariants, moving-target defense via statement shuffling and opaque Sovereign Guards, temporal attack-surface analysis. Blocks 312 attack vectors at <0.2% overhead; ~100× exploitation cost.
doi:10.5281/zenodo.19162019TXT · 38 KBZenodo - NetworkingPublicationCoreYggdrasil
YGGDRASIL: A Constitutional DNS Layer for User Safety, Privacy, and the Sovereign Internet
Constitutional DNS layer: name resolution governed by the same authority chains as execution. Enables a sovereign internet substrate in which user safety and privacy are structural, not advisory.
doi:10.5281/zenodo.19591259PDF · 19 KBZenodo - PhilosophyPublicationPhilosophicalDeep-Time Layer
The Universe Does Not Preserve All Information (V3): Detectability Collapse and the Mandatory Deep-Time Constitutional Layer for Sovereign AGI
Argues that physical detectability decays over cosmological time, so any sovereign AGI must carry a deep-time constitutional layer whose invariants survive observer collapse.
doi:10.5281/zenodo.19481152TXT · 24 KBZenodo - GovernanceWorking PaperCoreOctoReflex · Cerberus
Dual Governance Kernel Disclosure
Working paper. Discloses the dual-kernel governance design: a cognition plane that can only propose, and a reflex plane that contains. Defines the invariant L_reflex < L_cog and the privilege-separation guarantees that make conflation attacks structurally impossible.
In-repo research document · no DOIDownload · pending upload - GovernanceWorking PaperCoreTriumvirate · Ledger
Meta-Governance — Segments 1–3
Working paper. Three-segment treatment of meta-governance: how the governance system governs proposed changes to itself. Quorum thresholds (2f+1, 3f+1), anchor extension rules, and deterministic shadow execution required before any canonical commit.
In-repo research document · no DOIDownload · pending upload - GovernanceWorking PaperSupportingAudit Ledger
Admissibility Debt
Working paper. Introduces 'admissibility debt' — the accumulated cost of any AI action executed before its governance ticket was fully validated. Formalises ledger reconciliation and the SAFE_HALT obligation when debt exceeds bounds.
In-repo research document · no DOIDownload · pending upload - SecurityWorking PaperSupportingAEGIS Runtime
Project AEGIS
Working paper. AEGIS specifies the defensive perimeter for Project-AI: kernel-level enforcement hooks, capability authority chains, and the runtime that refuses any execution lacking a complete authority path back to the constitution. (Internal codename for a broader resilience engine.)
In-repo research document · no DOIDownload · pending upload - IdentityWorking PaperFoundationalIdentity Attestation
The 'I AM' Moment
Working paper. Constitutional procedure by which a Project-AI instance declares, signs, and binds its identity to a verifier set. Without a current 'I AM' moment, no action is admissible.
In-repo research document · no DOIDownload · pending upload - GovernanceWorking PaperCoreTriumvirate
Triumvirate Governance — Galahad, Cerberus, Codex Deus Maximus
Working paper. Three-validator governance design. Galahad attests to identity, Cerberus enforces invariants, Codex Deus Maximus arbitrates constitutional questions. Quorum is required for any non-trivial decision.
In-repo research document · no DOIDownload · pending upload - GovernanceWorking PaperSupportingRefusal Logic
NIRL — Negative Inference Refusal Logic
Working paper. Refusal logic for negative-inference cases: requests whose admissibility cannot be established positively. Defines deterministic SAFE_HALT triggers and audit-grade refusal reasons.
In-repo research document · no DOIDownload · pending upload - GovernanceWorking PaperSupportingOctoReflex · ESC
RH-Negative — Reflex/Halt Negative Procedure
Working paper. Formalises the path the reflex plane takes when neither ALLOW nor SAFE_HALT is fully justified by available evidence. Forces conservative escalation rather than implicit consent.
In-repo research document · no DOIDownload · pending upload - PhilosophyWorking PaperPhilosophicalConstitutional Theory
On Conflation: Why Self-Modification Must Be Externally Witnessed
Working paper. Formal argument that no system may unilaterally modify the rules under which it is judged. Conflation is identified as the root cause of unsafe self-modification; external witnessing is the structural remedy.
In-repo research document · no DOIDownload · pending upload - GovernanceWorking PaperSupportingGovernance-IDE
Local Coding CareTaker — Governed Coding Agent
Working paper. OpenAPI 3.1 specification for a local-first, governance-aware coding agent runtime: identity, capability declarations, execution policies, tool orchestration, workspace access, and signed audit decision records.
In-repo research document · no DOIDownload · pending upload