Independent systems builder

01 / 05

Useful systems,
carefully made.

I build at the intersection of applied AI, developer tools, and self-hosted infrastructure. The aim is simple: make complex systems easier to understand, operate, and trust.

02 / Selected work

Systems with a point of view.

A few threads I keep returning to: turning information into usable context, giving agents safer tools, and keeping personal infrastructure legible.

01

GBrain Knowledge infrastructure

A private knowledge layer for searchable context, citations, and agent workflows that stay close to the source.

View
02

Vector Architect Retrieval architecture

A source-led workspace for structured memory, integrity checks, and a clean MCP surface that other tools can extend.

View
03

Agent operations Runtime reliability

Practical work around agent sessions, process lifecycle, and the details that make automation trustworthy.

View
04

Home infrastructure Self-hosted systems

Small, useful infrastructure: network services, backups, and constrained devices that stay observable and recoverable.

View

03 / About the work

Clear interfaces.
Honest failure modes.

I like work that sits between the diagram and the lived reality: systems that another person can operate, inspect, and trust six months later.

Focus
AI systems · tooling · operations
Approach
Human-gated · source-led · durable
Now
Building useful things in public

04 / Open source

Recent on GitHub.

Open profile

Looking for public repositories…

05 / Notes

Small signals.

Build notes, field reports, and links worth passing on. The feed is intentionally small.

Connect

Have a useful problem?