Home
A simple place for my collected thoughts and notes.
Welcome! I'm Sam Stelfox, a security engineer and operations leader with a long-standing habit of taking things apart to see how they work. The best of my time belongs to my wife Hannah, our daughter Zelda, and our pup Cookie, with whatever is left going to tinkering with compilers, knowledge graphs, genetic algorithms, and whatever else catches my attention.
I use this site to keep notes on things I'm digging into, write the occasional blog post, and track whatever projects I'm tinkering with. If you want to know more, there's an about page with contact info.
Why Build Another Agent Harness
There are a lot of agent harnesses out there. So why build another one?
I've spent a lot of time in this space. I built several small agent systems in both Rust and Python, tried most of the popular frameworks, ran models from all the major providers and a bunch of open ones, experimented with custom LoRA layers and spec-driven task systems. Every setup taught me something about where things break down and I kept notes along the way.
What I wanted wasn't exotic. A system that runs on my hardware, manages agents as durable long-lived processes, connects to the communication channels I already use, and enforces real security boundaries between agents and data. Capability-based access control, taint tracking, domain isolation, per-process network filtering. These are all well-understood ideas with decades of prior art. The agent ecosystem just hasn't prioritized them yet because everyone's working on different problems.
Posts
- Why Build Another Agent Harness
- Secure Boot on Older and Unstable Motherboards
- Podman Socket Compatibility for Docker Tools
- Combining "Subscribers" in Rust's Tracing Library
- Logical Volume in Use
- Extracting Dracut Built initramfs
- Blender Loop Select in Cinnamon
- Fixing Hung Nginx Workers
- Fixing Dark Input Boxes in Firefox
- Merging Overlapping Subnets