
HangarX
An applied AI lab built on shared parts. Nothing gets built twice.
HangarX does not have one stack under everything. It has shared parts, and nothing gets built twice. Cortex is the deepest of them, the knowledge engine the agent line runs on. Brand DNA, UI primitives and pipelines are shared too, and each venture draws what it needs.
The cost nobody quotes
The first AI venture teaches you what it actually costs. Not the model. The rest.
Getting real business context into a form a model can use. Retrieval that returns the right thing. Memory that survives the session. Orchestration that keeps a chain of agents honest. Then brand, then UI, then the deploy pipeline. Months of it, and none of it is the product.
The second venture pays it again. So does the third. That is where applied AI labs quietly die: not from a bad idea, from re-buying the same foundation.
So we built the foundation first and gave it a name. Cortex is the knowledge engine: a unified knowledge graph, semantic retrieval, a memory and context layer, reasoning orchestration. One thing to harden, one thing to make fast, one thing to get right. Everything on that line is thin on purpose: know with Cortex, decide with Apex, distribute with Helix, teach with Academy. A vertical, not a rebuild.
What it bought
The newest work starts on a running system: knowledge layer live, agents deployed, brand locked, pipeline warm. What is left is the part that is actually new.
The same stack ships three ways. We run it for our own ventures, deploy it for a small number of clients, and co-found on it with people who bring the vertical and not the infrastructure.
Brand system
The brand got the same treatment. One locked brand DNA, then every surface rendered from it rather than designed again: product UI, print, packaging, out of home, and the brand world itself, generated in Northlit from the same source. Built once, used everywhere. Tap any tile to open it.
What is on it
Eleven things in flight. They are not the same kind of thing, so they are not counted as one.
Agents on Cortex

Apex
Strategy. Signals, scenario modelling and agentic analysis for founders and operators.
BetaHelix
Distribution. ICP targeting, campaign orchestration and multi-channel delivery, cloneable for customers.
In development
First-party products

Northlit
The lab’s AI design suite. Explore, direct, build, from the app or from any coding agent.

Second Brain
Your Obsidian vault becomes shared memory for Claude, Cursor and any MCP agent. Local first.

Academy
Generative podcasts and live multi-agent conversation, for leaders who want fluency rather than theory.
Beta
Open source, and what we made with it
GenAI Kit is a free production system for continuity-controlled GenAI films and graphic novels. The Mirror Protocol is the film we made with it: ten minutes, plus a 41-page graphic novel. It exists because the foundation was already paid for.
Proofs, not businesses
Neither is a company. Both exist to show that the stack makes new things cheap.
AI Voice
Raw, messy speech becomes clean written text.
In developmentGenerative Podcasts
Long-form audio built straight from a knowledge base.
In development
Portfolio
Two investments, both running on Cortex in different forms. They take more than the technology: we consult on the architecture and sit in their feedback loop.
Leviathan
Coastal intelligence for marine conservation. Automated ocean observatories watch for whales through fog, glare and darkness, and LeviathanOS turns the sensor stream into auditable, report-ready evidence. First observatory live at MBARI in Moss Landing.
Runs on CortexWay2Wise
Practice the human side of engineering. Their EQ Agent walks engineers through a listen, reflect and try loop on the interpersonal moments that stall projects.
Runs on Cortex
Pay the setup cost once.
The HangarX thesis
Role
HangarX builds vertical AI products on shared parts, so the setup cost is paid once and the next venture starts from a running system.
Technical direction
Co-founder and CTO. I own architecture and engineering direction across the lab.
Cortex
I own the knowledge engine the agent line runs on: graph, retrieval, memory, orchestration.
Agentic products
Agents that do real work, not demos. Apex first, Helix next.
Design & engineering
Design and implementation in one pair of hands, so the craft bar holds end to end.
- Applied / agentic AI
- Shared platform infrastructure
- Vertical SaaS for services
- Product design
- Full-stack engineering
- 0 → 1 product strategy
Next
HangarX is early and building in the open.
Visit hangarx.ai ↗











