Whitepapers

Technical documentation library: substrate, supply chain, codex, and more.

18 named models. One governed choice.

CAPPZ is model-independent. The title-bar picker writes the operator’s choice as a hash-sealed ModelSelected transaction; every app replays that same latest-wins record. Auto preserves both a cloud and local target, then routes from the selected primary slot.

Cloud · Lovable AI Gateway

Nine verified Google and OpenAI choices. Auto can keep one as the cloud primary or fallback.

  • Gemini 3.7 Flash google/gemini-3.7-flash · Google · fast
  • Gemini 3.1 Flash Lite google/gemini-3.1-flash-lite · Google · fast
  • Gemini 3.1 Pro (Preview) google/gemini-3.1-pro-preview · Google · premium
  • GPT-5.6 Luna openai/gpt-5.6-luna · OpenAI · fast
  • GPT-5.6 Terra openai/gpt-5.6-terra · OpenAI · standard
  • GPT-5.6 Sol openai/gpt-5.6-sol · OpenAI · premium
  • GPT-5.5 openai/gpt-5.5 · OpenAI · premium
  • GPT-5.4 Mini openai/gpt-5.4-mini · OpenAI · standard
  • ChatGPT (Instant) openai/chat-latest · OpenAI · standard

On this machine · Ollama / LM Studio

These starters seed the model wallet. Runtime discovery also exposes any other model installed on the operator’s endpoint.

  • Kimi K2 (Moonshot, open weights) kimi-k2:latest · open weights · local
  • Qwen 3 qwen3:latest · open weights · local
  • DeepSeek R1 deepseek-r1:latest · open weights · local
  • Llama 3 llama3:latest · open weights · local
  • Mistral mistral:latest · open weights · local

In this browser · WebGPU

Wallet-published browser models show download and local weight-custody status before execution.

  • Llama 3.2 3B (WebGPU) Llama-3.2-3B-Instruct-q4f32_1-MLC · WebGPU · local
  • Llama 3.2 1B (WebGPU) Llama-3.2-1B-Instruct-q4f32_1-MLC · WebGPU · local
  • Qwen 2.5 1.5B (WebGPU) Qwen2.5-1.5B-Instruct-q4f16_1-MLC · WebGPU · local
  • Phi-3 mini (WebGPU) Phi-3-mini-4k-instruct-q4f16_1-MLC · WebGPU · local

Visible, not enabled

These rows are deliberately disabled. They are not sent to Lovable AI Gateway and are not selectable today.

“We applied CAPPZ to Lovable, ChatGPT and Claude” describes the development environments where the discipline was forged. It is not the runtime catalog: ChatGPT is selectable now; Claude remains a visible, disabled bring-your-own-key entry.

The Autonomous AI Substrate

v3.4 — July 2026

One wallet container. Any skill. Zero rogue supply chain. Device root (ARM/Qualcomm TrustZone) → HD-addressed wallet containers → embedded admin agents → included skills (each with its own ontology, BPMN, edge functions) → notarized TX graph → cappz-store cache. CPM replaces npm. RepoZ replaces GitHub. Inter-Wallet Ops (cappz-sessions + chainlets + A2A) replace shared servers — off-chain private data plane, opportunistic on-chain anchoring.

Human-Optimized Supply Chain

v3.2 — March 2026

Zero-human supply chain architecture with SHIFT identity, provenance-as-a-service, and treasury commodity hedging integration.

Device-Rooted Trust — TrustZone Anchoring

Coming Soon

ARM instructions resident in the Qualcomm TrustZone notarize everything at the point of capture — eliminating deepfake at the device level. The L1 substrate beneath every CAPPZ deployment.

CFO Edition — Sovereign Treasury Agents

Coming Soon

Practical, deployable tools giving CFOs direct control over treasury operations, commodity flows, and compliance — without cloud vendors or intermediaries.

zIoT — Zero-Trust IoT Framework

Coming Soon

Trustless device attestation, smart-tag cryptography, and edge-compute orchestration for industrial IoT.

Chainlets — Local Blockchain Cache

Coming Soon

HD-derived chainlet architecture, anchor-block consensus, and subscription-based sync agent marketplace.