Sovereign AI Architecture Spec / v1.0

    CC BY-SA 4.0 · Open Spec

    Sovereign AI
    Architecture Spec

    A citable, openly-licensed reference for building sovereign AI infrastructure. One stack, five planes, two products — from the edge of a learner's cracked phone screen, up through cognition, community, market, and sovereignty, and back. For the conceptual framing, see the AI Sovereignty Framework.

    The shape we're building toward: an ARPANET for AI

    5 planes5 layers4 hyperagentsSNBH state vectoroffline-first

    The whole stack

    One stack, five planes.

    HumaneFrame (the generative half — pedagogy, AI runtime, skill verification) and the Diné Talent Marketplace (the allocative half — supply, demand, matching) share one membrane: the Personal Capability Record.

    EDGE PLANELearner & employer devices · mobile-first · offline-firstAlastairlearnerArtifactswriting · audio · video · codePCRlearner-owned ledgerLOCAL SOVEREIGN AI PLANERuns on-prem at the Chapter House · DGX Spark · offlineLibrarianartifacts → RSDsSakifine-tuned local modelSNBHstate vectorGFCSocratic routingSwarm4 hyperagentsCOMMUNITY PLANEChapter House · the human layer that holds it allThe Weavernavigator · crisisMentorsendorse competenciesChapter Eventscircles · ceremoniesNETWORK PLANEDiné Talent Marketplace · supply meets demandJob Ingestjobs · sectors · salaryMatcherfit · gaps · explanationUpskillingNTU · Diné CollegeEmployer Portalview PCRsSOVEREIGNTY PLANENavajo Nation governs · DODE oversight · open standardsTribal Governancemodel + algo oversightAggregate AnalyticsNation-ownedOpen StandardsOpen Badges · CLR · RSDinteractsverified competencycrisisendorsessharing windowgap plannew questsgovernsgovernsanonymizedanonymizedschemaHUMANEFRAME × DINÉ TALENT MARKETPLACE — UNIFIED ARCHITECTURE
    data flowgovernance · oversight · anonymized signal

    Roadmap

    The sovereignty arc.

    Phase 01

    Pilot

    Cloud-gateway Saki + Aspire Ability marketplace

    Prove the thesis. Real Navajo learners. Real jobs. Real verified competencies. Cloud-hosted intelligence with sovereign data ownership at the edge.

    Phase 02

    Lab

    Locally-tuned LLM at Diné College / NTU

    Move the model. Domain-specialized LoRAs trained on Nation-authored corpora. DGX Spark deployment. Bellman-equation routing for community-aware decisioning.

    Phase 03

    Mesh

    Chapter House mesh — sovereign by infrastructure

    Move the infrastructure. Local compute at Chapter Houses. Offline-first. Federated. The Nation operates its own AI without dependency on any external provider.

    Technical reference

    The deep stack — expand to explore.

    Each section below is a self-contained chapter of the architecture. Open what's relevant to you; the rest stays out of your way.

    System map

    The whole picture — four planes

    Alastair's space, Saki's intelligence, the labor market, and the infrastructure beneath. Red dots mark architectural decisions still being worked through.

    Plane 01 · Alastair's space
    Human roles
    Alastair
    learner
    Parent
    sharing window
    Teacher
    Mentor
    Peer
    Saki's surfaces
    Tutor
    Socratic quests
    Librarian
    discovers + curates
    Writing lab
    scaffolds
    Artifacts of learning
    Goals
    Work plans
    Quests
    Sharing windows
    per-viewer consent
    Plane 02 · Saki — primary agent (Murasaki)
    Triage / route / accompany
    System 1
    fast reflex
    System 2
    deliberate
    System 3
    meta / oversight
    State + memory
    SNBH state vector
    c, e, p, k (Diné)
    PCR + goals
    Weaver protocol
    Rosa / Weavers
    Knowledge substrate
    Career ontology
    competencies
    Curriculum
    rubrics + scaffolds
    Artifacts + docs
    evidence trail
    Rules engine
    Plane 03 · Labor market + community context
    Labor market + careers
    LMI pipeline
    17 sources · 18 scrapers
    Employers
    Job A · Job B · Job C
    Prof. domains
    shared RSDs across roles
    Community context
    Language / culture / K'é
    Resources / PM
    Collaborative
    peer matching
    Evolutionary loop
    feedback into ontology
    Plane 04 · Infrastructure
    High Church (cloud)
    Gemini / Claude / Llama API
    fast LLM inference
    GCP / neutral cloud
    Phase 1
    LLM Gateway
    routes by task
    Navajo Enclave (sovereign)
    DGX Spark / local models
    private · localized · tuned
    dLoRA + chapter mesh
    Phase 3

    Every competency signal: L0 self-attested → L1 inferred → L2 assessed → L3 endorsed → L4 validated (OBv3)

    Five coaching modes

    Saki adapts its register to who is in the seat. Same agent, five postures.

    Learner
    Alastair herself — first-person growth.
    Parent
    Guides a child's path through a sharing window.
    Teacher
    Operates inside the same system as the learner.
    Mentor
    Endorses competencies; sees PCR slices.
    Peer
    Collaborates on shared quests + artifacts.
    Confidence tiers

    Every claim Saki records carries a provenance tier. L4 alone is portable across institutions.

    1. L0
      Self-attested
      Alastair claims the skill.
    2. L1
      Inferred
      Saki infers from behavior.
    3. L2
      Assessed
      Saki probes with rubric tasks.
    4. L3
      Endorsed
      A mentor or peer vouches.
    5. L4
      Validated (OBv3)
      Issued as a verifiable credential.
    Footnotes

    Numbered red dots throughout the map are tappable. They expand on key architectural mechanisms.

    1. 1System 2System 2 leverages the SNBH vector for routing and adjustments.
    2. 2Artifacts + docsArtifacts are versioned (along with metadata) to maintain history.
    3. 3Validated (OBv3)Federated implementation and crosswalking across issuers.
    4. 4LibrarianLibrarian spins up and maintains domain, profession, and career repositories that are dynamically updated.
    5. 5CollaborativePeers are matched for collaborative learning.
    6. 6ParentParents are also learners — they can work on their own learning while also functioning as Alastair's mentor.
    7. 7Prof. domainsDomains are managed by the Librarian (governed by fine-tuned LoRA).

    User journey

    Alastair's path — seven steps

    From first conversation with Saki to a lifetime of accumulating verified competencies.

    Step 01Explore

    Alastair opens HumaneFrame on her phone. She meets Saki. She talks about what she's interested in — jobs at the Navajo Housing Authority, remote work, project coordination. Saki doesn't present a dropdown. She listens. The SNBH state vector begins initializing.

    Core infrastructure

    The 5-tier stack

    Edge → Engagement → Intelligence → Data → Safety Net. Click any layer for components and tech.

    The entry point. Built to meet the learner exactly where they are, regardless of hardware or connectivity.

    Progressive Web App

    PWAService WorkerManifest

    Mobile-first design for cracked Android screens, with "Progressive Escalation" to desktop for complex tasks.

    Local-First / CRDT Sync

    IndexedDBCRDTAutomerge

    IndexedDB local storage ensures the system works entirely offline in broadband dead-zones, syncing immutably to the cloud only when a connection is stable.

    Fluid Multimodality

    WASMWhisper-liteWebRTC

    Edge-computed Speech-to-Text (WASM Whisper-lite) allows learners to bypass the cognitive load of typing and speak naturally about their lived experiences.

    How the system extracts signal from the noise of human experience.

    Saki — The Orchestrator

    LLMDialogue EngineState Machine

    The user-facing agentic partner. Saki engages in a multimodal "Diagnostic Dialogue" — no dropdowns.

    The Broken Thing Sandbox

    SandboxDockerEphemeral Env

    Replaces multiple-choice testing. Saki provisions secure, ephemeral environments to assess executive functioning, resilience, and problem-solving under productive frustration.

    Calibration Handshake

    BaselineFriction DialConsent

    The learner explicitly sets their friction/empathy baseline at "Minute One."

    The proprietary cognitive engine behind Saki. This is the technical moat.

    System 1 — Sensorium

    LLMStreamingAttention

    Fast associative LLM that ingests real-time signals and generates candidate responses.

    System 2 — Security Enclave

    Bellman Eq.GFCDeterministic

    Deterministic routing backend. Calculates the Murasaki Bellman Equation to enforce the Generative Friction Constraint. Applies the "Ezekiel Penalty" to mathematically block cognitive surrender.

    System 3 — Hyperagent

    Meta-learningEvolutionaryEquity Fn

    Self-referential evolutionary loop that monitors efficacy and autonomously improves coaching strategies — strictly bound by the equity objective function.

    The infrastructure of learner sovereignty. We store the messy truth and export the market standard.

    Schema-on-Need

    Librarian AgentOSNRSDs

    Ingests unstructured, authentic human reality. The Librarian Agent parses at inference time to tag with machine-readable Rich Skill Descriptors.

    Personal Capability Record

    CLROpen Badges v31EdTech

    A learner-owned, portable, immutable ledger built on 1EdTech open standards. It belongs to the learner, not the institution.

    Labor Market Grounding

    jobsdata.aiEROsReal-time

    Hydrates the system with Employer Reference Objects using real-time, localized job postings to ensure all learning maps to actual demand.

    The ultimate fail-safe. AI should not solve human crises.

    Triage — Rule-Based

    ThresholdDeterministicNot LLM

    When the SNBH emotional load vector spikes, the system halts learning and triggers escalation. Explicitly deterministic — generative LLMs are documented as dangerous in crisis contexts.

    Routing — RAG Directory

    HSDSFHIRGravity Project

    Queries HSDS-compliant directory of vetted, local community resources. Integrates Gravity Project FHIR SDOH standards. 90–96% precision vs general-purpose LLM hallucination.

    Accompaniment — Human Weavers

    Warm HandoffChapter HousesCompensated

    A trained, compensated Navajo Nation community navigator receives warm handoff from Saki and stays through resolution.

    Epistemological core

    SNBH state vector

    s⃗ₜ = [cₜ, eₜ, pₜ, kₜ]ᵀ — the live four-axis vector Saki routes through. Optimization target is Hózhó, not task completion.

    cₜ
    Nitsáhákees
    Mind / Cognitive Load

    Saki reduces friction when overwhelmed; adds Socratic challenge when coasting.

    eₜ
    Iiná
    Body / Emotional Load

    Trauma and exhaustion are first-class signals. Triggers Weaver Protocol when threshold exceeded.

    pₜ
    Nahat'á
    Place / Situational

    High-dimensional. Grounds logic in the learner's actual organization, geography, and culture.

    kₜ
    K'é
    Community / Relational

    Tracks relational connections. Actively moves learner from isolation toward kinship.

    Multi-agent system

    The hyperagent swarm

    Four agents — Mapper, Designer, Instructor, Provocateur — that compose Saki's behavior.

    Learning theory

    The pedagogical framework behind the swarm

    How learning theory is formalized into computable constructs and routed to agents.

    Theory → Computable Construct

    Pedagogical formalization

    Four functional layers organize a century of learning theory into computable constructs that route to specific components of the Hyperagent Swarm.

    LAYER 01

    Teleology

    Why and for whom — sets goals, learner stance, ethical frame
    Bloom (mastery)Freire (critical pedagogy)Bandura (agency)Knowles (andragogy)
    Formalizes asSNBH state vector + Charity reward function
    Routes toSystem 2 enclave — governs every decision
    LAYER 02

    Architecture

    How to design learning — pathways, evidence, ZPD
    McTighe (backward design)Mislevy (evidence-centered)Vygotsky (ZPD)
    Formalizes asKnowledge Graph + Employer Reference Objects
    Routes toThe Ontologist + The Architect
    LAYER 03

    Mechanism

    How learning actually happens — task, feedback, retention
    Merrill (task-centered)Gagné (nine events)Bjork (desirable difficulty)Gibbons (model-based learning)
    Formalizes asTask templates + Generative Friction Constraint
    Routes toThe Instructor + The Provocateur
    LAYER 04

    Affect & Identity

    Who the learner is becoming — agency, kinship, dignity
    Deci & Ryan (self-determination)Dweck (mindset)K'é (kinship)
    Formalizes asSNBH emotional + relational vectors
    Routes toSaki dialogue tone + Weaver Protocol triggers

    One Coaching Interaction

    Runtime pedagogical flow

    When Saki coaches Alastair through a Financial Reporting quest, each step is governed by a specific, formalized learning theory — not improvisation.

    1. STEP 01

      Session opens

      Alastair sets her SNBH sliders

      Knowles — andragogy

      Self-directed adults control their own learning conditions

    2. STEP 02

      Goal confirmed

      Financial Reporting gap identified

      McTighe — backward design

      Define mastery evidence first, then design the path

    3. STEP 03

      Difficulty calibrated

      Bloom's Apply level — not Remember, not Create

      Vygotsky — ZPD targeting

      Stay in the zone between can-do and can't-yet

    4. STEP 04

      Task presented

      NHA variance report — a real artifact

      Merrill — task-centered instruction

      Real task, activate prior knowledge, then apply

    5. STEP 05

      Alastair builds artifact

      Constructs the variance report; Saki watches

      Bjork — desirable difficulty

      Productive struggle builds durable competency

    6. STEP 06

      Friction injected

      Saki withholds the answer; asks a sharper question

      Generative Friction Constraint

      Prevent cognitive surrender — protect the learner's thinking

    7. STEP 07

      Artifact reviewed

      Competency claim written to PCR

      Mislevy — evidence-centered design

      The artifact itself is the credential evidence

    8. STEP 08

      Identity update

      Alastair sees herself as someone who can do this

      Bandura — self-efficacy

      Mastery experience is the strongest source of agency

    Mathematical foundations

    Core equations

    The Generative Friction Constraint and the Charity Reward Function — what mathematically blocks cognitive surrender.

    Generative Friction Constraint

    Ycog = α · Fprod − β · Ssurr

    α = empathy multiplier (behavioral telemetry)

    β = penalty for cognitive surrender

    Fprod = productive friction level

    Ssurr = surrender signal intensity

    Charity Reward Function

    Rχ(s⃗, a) = Λ(s⃗) · ΔH(s⃗, a) − Ω(a)

    Λ = Rawlsian multiplier (scales with acute distress)

    Ω = Ezekiel Penalty (blocks "solving" over coaching)

    ΔH = delta toward Hózhó (holistic balance)

    s⃗ = SNBH state vector

    Sovereignty & structure

    The PCR & the dual-entity model

    Learner-owned credentials on open standards; a 501(c)(3) + for-profit pairing that keeps the moat in relationships, not data.

    Data Sovereignty

    Personal Capability Record

    What it is

    Learner-owned · Portable · Immutable · Sovereign · Not institution-controlled

    Open standards

    Open Badges v3 · CLR · 1EdTech · Tribal data sovereignty

    Opt-in onlyGranular controlNever soldNever for adsLearner chooses

    Corporate Structure

    Dual Entity Model

    HumaneFrame Institute

    501(c)(3) · Nation relationships · Federal grants · Employs Weaver network

    HumaneFrame Inc.

    For-profit · Platform builder · Venture-ready · Licenses to nonprofit

    CC BY-SA 4.0 specsTrademarksNation data sovereignMoat = relationships
    CC BY-SA 4.0

    Cite this spec

    An open spec, freely adoptable.

    The Sovereign AI Architecture Spec is published under Creative Commons Attribution 4.0. Peer Nations, institutions, and researchers are welcome to adopt, adapt, and extend it — with attribution.

    Plain citation

    HumaneFrame. (2026). Sovereign AI Architecture Spec (v1.0). Aspire Ability Foundation. https://humaneframe.org/architecture

    BibTeX

    @techreport{humaneframe2026spec,
      title  = {Sovereign AI Architecture Spec},
      author = {HumaneFrame},
      year   = {2026},
      number = {v1.0},
      institution = {Aspire Ability Foundation},
      url    = {https://humaneframe.org/architecture},
      note   = {Licensed CC BY-SA 4.0}
    }