Running AI Coding Agents in Production: My 2026 Stack
Everyone has an opinion about AI agents. Almost nobody publishes their actual production setup — the gateways, the MCP servers , the credential handling, the monthly bill. This is mine, as of August 2026, with real numbers and the failures included. I run coding and automation agents daily for real
Posted on Oct 30 • Originally published at agentjournal.dev
Everyone has an opinion about AI agents. Almost nobody publishes their actual production setup — the gateways, the MCP servers, the credential handling, the monthly bill. This is mine, as of August 2026, with real numbers and the failures included.
I run coding and automation agents daily for real work: this site, open-source tooling, and the automation that runs my infrastructure. Here's the stack, layer by layer.
I don't use one agent for everything. Using the right tool per task is the cheapest optimization available:
The rule I've landed on: a coding agent that runs unattended is an ops problem, not a coding problem. Which is why the layers below matter more than which agent you pick.
Routing through gateways instead of calling providers directly is the single biggest sanity improvement. I use three:
This is where most agent setups are a disaster waiting to happen. My rules:
The MCP layer is where the real leverage is. Currently running:
The lesson: a well-scoped MCP server beats a prompt telling the agent to "be careful" every time. If the agent can't reach it, it can't break it.
The trick is boring: route the expensive calls through the free tiers, self-host the repetitive work, and let the gateways absorb the variance. I've seen the same setup run $200+/mo when the routing is lazy.
The agent you pick matters less than the plumbing around it: gateway routing, credential hygiene, scoped MCP access, and a tailnet. Get those right and you can swap models and agents freely — which is exactly what you'll want to do, because this space moves monthly.
This is the first post in what will be a series on the details: MCP server design, gateway cost engineering, and credential handling for agents. If you're running agents in production too, I'd like to hear what your stack looks like.
Disclosure: some links in this post are affiliate links — see disclosure.
Originally published at agentjournal.dev.