INTELLIGENCE ARCHITECT | COGNITIVE INFRASTRUCTURE FOR AGENTS
Constructing High-Dimensional Intelligence Infrastructure.
Engineering at the intersection of Epistemic Memory Systems, Agentic Context Engineering, and Cognitive Infrastructure. Focused on bridging the gap between retrieval and reasoning through structured doubt, externalized epistemics, and high-performance agent harnesses.
01 // SYSTEM ARCHITECTURES
- LEAP/CITE: Layered epistemic protocol with stratified types and write-time coherence enforcement.
- VEIL: Local-first agent memory — sqlite-vec embeddings, FSRS decay, deterministic eviction.
- AGENT HARNESSES: Claude Code plugins and multi-modal agent lifecycle tooling.
- DATA PIPELINES: Automated ETL for graph-structured knowledge bases via Dagster.
02 // ONGOING EXPLORATIONS
- LeAP: Layered Epistemic Agent Protocol — stratified memory with warrant-backed claims. (shipping as Veil)
- JEPA-native agent architectures: latent-space reasoning without text projection.
- AGM-compliant belief revision in production agent loops.
- Externalized epistemics at scale: distributed warrant chains.
"STRUCTURING THE UNSTRUCTURED."




