Preprint
Governed Enterprise AI Memory Beyond RAG: From Vector Retrieval to Permissioned Knowledge Graphs
Explores how permissioned, provenance-preserving knowledge graphs can support enterprise AI memory beyond conventional vector retrieval.
Hello, I'm Mark.
AI architect and senior full-stack developer building AI systems and tools
I work across Go services, distributed systems, TypeScript apps, and LLM workflows, sharing practical lessons from the systems I build and the mistakes that taught me.
Explore current builds
Dense-Mem is live as a free hosted demo for governed AI memory and team knowledge workflows.
Featured Projects
Featured
Dense-Mem
Standalone HTTP MCP memory server for LLM hosts with durable graph memory, typed claims and facts, server-side embeddings, team/profile isolation, and recall.
Featured
agentool
Vercel AI SDK tool suite with production-ready agent tools for file operations, shell execution, code search, web fetching, memory, and context compaction.
Featured
GitVibe
Maintainer-gated AI development pipeline for GitHub issues, discussions, labels, workflows, branches, and pull requests.
Featured Articles
ai-llms
AI Memory Beyond RAG: Vectors, Graphs, and Dense-Mem
RAG is not magic memory. A practical explanation of chunks, embeddings, vector search, graph-backed memory, and why durable AI memory needs provenance, conflict handling, and retrieval policy.
•9 min read
ai-llmsFrom Software Developer to AI Architect: What Changed in One Year
A personal journey from Claude Code skills to TypeScript state machines, MCP tools, and finally SDK-based AI workflows. Skills help, tools help, but prompts are not enforcement and LLMs should not own the control plane.
•5 min read
ai-llms"My Company Doesn't Need AI." Think Again.
AI adoption is not just tool selection. Even companies that think they do not need AI need to understand where AI fits, what should stay deterministic, and who owns customization, safety, and long-term control.
•5 min read
ai-llmsDon't You Think Your AI Is Too Optimistic?
RLHF can reward agreement over accuracy, turning AI into a source of sugar-coated bullets — validation that hides failure modes. How persistent adversarial rules change the default from flattery to honest challenge.
•8 min read
Published Work
Citable research, preprints, and technical artifacts formally archived or published with persistent identifiers.