I help AI coding agents work on codebases too big for them

I build open-source tools — code knowledge graphs, code intelligence, and architecture tooling — that give coding agents the context they need on large and legacy systems. Forty years of engineering, now aimed at the gap between adopting AI and getting it to work on real code.

Read the blog Subscribe

  • symgraph — a knowledge-graph MCP server that gives agents a real map of a codebase
  • tropism — architecture rules an agent can actually check: import cycles and layering across ten languages, with no build and no network
  • forge — describe, render, and lint architecture from a single file
  • bx — run local MCP servers as native binaries, without a Node or Python runtime

All projects on GitHub →

Building resilient, scalable, and maintainable systems. From event-driven patterns to domain-driven design, I write about the architectural choices that shape successful products.

Rooted in software craftsmanship, TDD, and clean code. I argue for technical health over technical debt, and for continuous improvement in the craft.

The new frontier of AI-assisted development, from vibe coding to knowledge graphs for agents. I look at how AI is changing the way we build.

Looking for where to start? These are the pieces that have held up best — the tools change, the problems don’t:

Stay up to date with the latest thoughts on software engineering and architecture.

View All Posts