My home internet died for half a day. So did every agent I had. · bostrat

Essay · Durability

My home internet died for half a day.<br>So did every agent I had.

joey<br>August 11, 2026<br>6 min read

I had my laptop open at Java on Ocean in the Ingleside neighborhood of<br>San Francisco. I have a penchant for their dirty chai latte. At the time, I had a couple of<br>agents working in parallel and a window of about an hour before I had to mobilize. And just<br>as I took my first sip, the agent replies stopped coming in.

This was in June. I was five miles from my apartment with an immovable<br>schedule: back-to-back appointments, none of them cancellable, none of them near home. What<br>I didn't know yet, sitting there with a fleetingly warm beverage and a loading spinner that<br>wouldn't resolve, was that my apartment's internet had gone out and would stay<br>out for half a day. And that this single fact had just ended my ability to do any real work<br>at all.

What I built

Like a lot of people who've gotten serious about coding agents, I had moved mine off my<br>laptop and phone and onto a homelab: a Raspberry Pi in my apartment, running Claude Code and<br>Codex sessions inside tmux, reachable from anywhere over WireGuard. It felt like infrastructure.<br>Sessions survived closed laptop lids. I could check on a long run from my phone. The Pi never<br>ran out of battery and was accessible 24/7 (at first).

That morning it was grinding away on another of my projects while I watched from the café.<br>Steady work on three different git repositories at once — ideas I'd sketched out and sent to<br>the backlog.

Then the wire at home died. I got a ping from my ISP about an unplanned outage. Resolution<br>time unknown.

every road home, dead

$ wg-quick up home && ssh pi

ssh: connect to host pi port 22: Operation timed out

$ ping pi

--- pi ping statistics ---

12 packets transmitted, 0 received, 100% packet loss

And sitting there, enjoying my coffee, pondering the incident, powerless to deploy my<br>army of agents, I came to a key insight.

Every path to the Pi ran through my home router — the WireGuard tunnel, SSH, the little<br>web terminal I'd built on top — so my access was gone. But the less obvious half mattered<br>more. A coding agent isn't a program that runs on your box; it's a loop between your<br>box and a frontier model's API . No internet, no model, no agent. The Pi wasn't<br>stranded mid-task, faithfully working while I was locked out. It was inert.

home ISP dies · half a day

One wire, two failures: no way in for me, no way out for the agents.

"Just start another session"

I wasn't completely without options, and this is the part worth being honest about.<br>Session resume is a solved problem: I could clone the repo onto my laptop, open Claude Code<br>right there at the table, and be talking to a model in a few minutes. The model doesn't care<br>which machine it's talking to.

But that session wouldn't be my setup. It was on a laptop on public wifi, without the<br>compute, the environment, the guardrails, or the developer flexibility of the box I'd spent<br>months shaping. It could write and edit code. It couldn't be the bespoke harness I had built<br>for velocity and reliability.

It could write and edit code. It couldn't be the bespoke harness I had built for velocity and reliability.

And then there are the walls. Every agent user knows both. Sometimes the model just can't<br>crack it. You can feel it circling, and no amount of re-prompting gets it there. That wall<br>gets lower by the week as the models get better, but it hasn't disappeared. The other one is<br>usage: you simply run out. The plan taps out, always mid-thought, and picking it back up is<br>painstaking.

Both walls have the same exit. You take the work somewhere else: another agent, another<br>model, another plan. And that part is genuinely awful: copy-pasting context into a fresh<br>window, re-explaining what you were in the middle of doing, hoping you remember the pieces<br>that matter. Twenty minutes of archaeology each time. And you never fully trust what comes<br>out the other side.

So the failure wasn't that I lost files. It's that the work wasn't portable — not<br>across machines when the network died, and not across agents when I hit a wall. And this<br>wasn't even the Pi's first version of that lesson: run three Claude Code sessions at once,<br>each comfortably using a gigabyte or more, and it OOMs and reboots, taking every<br>session down with it. Same shape, different resource.

Sessions should be a medium, not a process

I did look for something to buy, and there's more of them each month: hosted boxes you can<br>rent, tools for reaching the machine you already own, orchestrators that run a dozen agents at<br>once — several of them free and genuinely good. What I kept not finding was the part after the<br>session starts. When I hit a wall I want to hand the work across — the conversation and the<br>working tree, not a summary — to a different vendor's agent, mid-task, and get it back. I want<br>a delegated side quest to come home as a merge,...