Systems Architecture Publications
Empirical whitepapers, SQL/AST schemas, and reproducible benchmark teardowns organized across the 4-layer local-first AI stack: bare-metal compute & cascade routing, relational PostgreSQL/MCP working-memory substrates, transactional execution harnesses, and air-gapped statutory/contract intelligence.
Multi-Tier Cascade Routing Architecture: Slashing Enterprise Inference Budgets by 60–80%
In multi-turn coding agents, sending every prompt turn directly to frontier reasoning models creates massive economic waste. Discover how krusch-cascade-router achieves an 80.72% accuracy score at $0.21/1K cost on the RouteWorks RouterArena benchmark through a dual-stage hierarchy: microsecond syntactic CPU gating (<15µs, $0.00 routing tax), neural centroid classification (<50ms), and speculative parallel hedging.
Microsecond Syntactic Gating, Neural Centroids & Operating Planes
Eliminating the 500ms LLM routing tax and unifying local bare-metal GPU pools with PostgreSQL state planes.
⚡ Multi-Tier Cascade Routing Architecture: Slashing Enterprise Inference Budgets by 60–80%
Stage-0 syntactic CPU gating (<15µs, $0.00 routing tax), Stage-1 neural centroid escalation (<50ms local embedding), speculative parallel hedging, token Pareto skew, and RouteWorks RouterArena benchmark disclosures.
Read Cascade Routing Whitepaper →⚡ Postgres as the State Plane: Why Side Effects Require a Transaction Manager
A language model is a probabilistic sampler; side effects require a transaction manager. How krusch, krusch-pre-router, krusch-cascade-router, and krusch-context-mcp unify into an invariant-gated developer harness.
3-Tier MCP Ecosystem: Governed Memory, Git DAG / AST Graphs & Fleet Filesystems
Replacing flat sliding-window RAG with ACID decision lineage, relational AST caller/callee graphs, and SHA-256 page-indexed OS filesystems.
🧠 Beyond Flat Vector RAG: What Makes krusch-context-mcp Special
Why flat vector RAG fails coding agents. Deep dive into the radical 5-verb discipline (retrieve, remember, revise, nudge, health), span-grounded provenance drift healing, and temporal lineage.
🌳 krusch-git: Git DAG Indexing, Relational AST Symbols, and Hybrid Recency Search for AI Coding Agents
Why grep and flat vector RAG fail autonomous coding agents. Git DAG objects in PostgreSQL 16 + pgvector, zero-dependency AST lexing, recursive multi-hop caller/callee CTEs, and exponential temporal decay.
Read krusch-git Architecture Deep Dive →🗂️ krusch-fs-mcp: OS Filesystem Page Memory, SHA-256 Drift Detection, and Multi-Node Fleet Indexing for AI Agents
Turning unstructured OS directories, PDFs, DOCX, systemd units, and /etc/fstab across an 8-node SSH fleet into layout-true page trees with SHA-256 drift-verified PageMemory annotations and secret-redacted .env indexing.
⚡ Architecting Code-Agent Retrieval & Memory: Beyond Naive Vector Search
Why sliding-window RAG fails on codebases. Single-store PostgreSQL 16 + pgvector HNSW, structural symbol extraction, SQL Reciprocal Rank Fusion (RRF), and empirical benchmarks (8.2ms P50).
Read Retrieval Architecture Paper →⚡ Sovereign Context & Working-Memory Architecture for Coding Agents
Decoupling Enterprise Access Gateways from the Sovereign Context Plane and Safe Execution Harness. Tool profile projection, stratified lambda-decay priors, and PostgreSQL 16 durability.
Read Enterprise MCP Hub Paper →2-Phase Commit Coding Harnesses, Swappable Storage & Voice-First Execution
Enforcing Bubblewrap container sandboxes, PostgreSQL 2PC apply journals, Polygres Cloud sync, and sovereign personal assistant workflows.
🛡️ The Krusch Coding Harness: Why Autonomous Code Agents Require a Transaction Manager, Not a Prompt
Why unconstrained file writing breaks coding agents. Pre-commit SHA-256 diff staging, Bubblewrap container isolation, row-locked catalog FSMs, and storage-engine 2PC apply journals.
Read Harness Architecture Deep Dive →💾 Swappable Substrates: Powering Agent Memory & Codebase Graphs with KruschContext, KruschGit, and Polygres
How swappable storage drivers let AI coding agents run on local zero-Docker SQLite/PostgreSQL or sync seamlessly with Polygres Cloud without changing a single MCP tool definition.
Read Swappable Substrates Paper →🚀 Local-First Core, Hybrid Cloud Elasticity: Decoupling Agent Memory
A practitioner's analysis of coding-agent memory topologies: SQLite edge caching, PostgreSQL durability, embedding parity pitfalls, and two-stage HNSW decay indexing.
Read Cloud Elasticity Deep Dive →🛡️ Introducing Krusch Companion: A Sovereign, Voice-First Personal AI Assistant & Dual-Axis Daily Execution Engine
Complete guide to krusch-companion: Voice-to-Text capture, how the Dual-Axis Priority Board solves the Priority Paradox, the <holodata> agentic proxy, and a 10-minute daily efficiency playbook.
☁️ Introducing G-Krusch: A Sovereign Google Workspace Hub, Hybrid Drive RAG & MCP Bridge
Complete architectural deep dive into G-Krusch: cloud-synced agent.md steering, 3-tier 1,024-dim semantic + SQLite FTS5 BM25 Drive RAG, 3-tier PDF extraction, 12 MCP tools, and NIST AES-256-GCM security hardening.
Layout-True OCR Coordinates, Statutory Precedence DAGs & Contract Compliance
100% air-gapped document ingestion (KruschNexus), 0.00% False Support Rate statutory grounding (KruschLaw), and relational contract-vs-statute join engines (KruschBiz).
⚖️ The Sovereign Triad: Unifying Document Ingestion, Statutory Graphs, and Agentic Working Memory
How KruschNexus (layout-true ingestion), KruschLaw (statutory authority & assertion grounding), KruschBiz (contract graphs), and KruschContext MCP create a closed-loop, self-auditing intelligence substrate.
Read Sovereign Triad Architecture Essay →⚖️ Citations Die in Local RAG: Why We Built KruschNexus and What It's For
Why arbitrary token slicing destroys document citations. Heldout evaluation of 7 parser families (100% citation accuracy, 96.2% span precision) and layout-aware 72-DPI bounding-box architecture.
Read KruschNexus Architecture Deep Dive →⚖️ Why We Built KruschLaw: Local-First Legal RAG & Ordinance Intelligence
Why generalist RAG fails in statutory law and municipal codes. Two-pass assertion grounding achieving 0.00% False Support Rate on golden benchmarks, versioned statutory precedence graphs, and verifiable purge.
Read KruschLaw Architecture Deep Dive →💼 Why Semantic Similarity Isn't Governing Precedence: What Makes KruschBiz Different From Generic Business RAG
Why flat vector search fails on commercial contracts. Confirmed-edge precedence graph resolver, unexecuted draft isolation, materialized effective slots, and The Join compliance engine.
Read KruschBiz Architecture Deep Dive →📦 Authority Packs: Certified Rulebooks for Enterprise AI — Sovereign Domain Scoping vs. Vector Bleed
Why enterprise buyers don't buy retrieval. How bounded, versioned rulebooks enforce O(1) token budgets, pre-extracted numeric slots, and physical citation truth across law, finance, and enterprise contracts.
Read Authority Packs Whitepaper →⚡ The Ingestion Imperative: Why Retrieval Quality Is Bounded Before the Model Reads a Single Word
Why wrong retrieval is the dominant root cause of enterprise AI failure. Deep dive into embedding space geometry, parser contracts, citation spines, and how the structured fix itself fails.
Read Systems Architecture Note →