Design Decisions

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

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