:PROPERTIES:
:ID:       e32290a0-a02a-4af7-ae22-243d04a7ac82
:CREATED:  [2026-05-24 Sun]
:ID:       0a33bd83-ff3c-4eac-bc97-83eb6702051a
:END:
#+title: Design Decisions
#+filetags: :passepartout:architecture:design:

The rationale behind key architectural choices — split by topic. Each file covers one major design domain.

- [[file:foundation.org][Foundation]] — non-negotiable identity, single agent, unified memory, Org-mode as AST, homoiconicity
- [[file:the-two-brains.org][The Two Brains]] — probabilistic-deterministic split, four pillars, dispatcher as learning system
- [[file:safety-self-preservation.org][Safety & Self-Preservation]] — self-preservation, type-level gates, layered signal authentication
- [[file:the-symbolic-engine.org][The Symbolic Engine]] — five architecture options, chosen path, ephemeral-first, gate bootstrap, LLM as proposer, cardinality policies, ontology, awakening, Merkle DAG, fact interface
- [[file:knowledge-sources.org][Knowledge Sources]] — Wikidata as entity backbone, MOMo empirical validation
- [[file:implementation-properties.org][Implementation Properties]] — performance, provenance chain as product
- [[file:engineering-infrastructure.org][Engineering Infrastructure]] — REPL, cybernetic loop, observability, literate programming, evaluation harness, MCP strategy, local-first, token economics, time awareness, definite description resolution
- [[file:validation.org][Validation]] — Whitehead, McCarthy, Marcus, CREST, competitive argument
- [[file:open-questions.org][Open Questions]] — unresolved design decisions
- [[file:relation-to-passepartouts-existing-architecture.org][Relation to Existing Architecture]] — how the neurosymbolic engine extends the current design