How we built "clanker infrastructure" — autonomous, network-isolated AI agents that pick up tickets, design, implement, and ship PRs through a locked-down container factory provisioned with formae itself.
How formae's core concepts — targets, resources, resolvables, and stacks — compose into one infrastructure graph, and why the power is in how they combine rather than in any one of them.
How formae's plugin SDK evolved across three iterations — from an in-process actor system to independent, hot-swappable plugin binaries on a schema we can change without breaking the fleet.
When your infrastructure code is up to date, there is no drift. How formae detects out-of-band changes and lets you reconcile — or absorb — them, instead of fighting drift.
A practical guide to the actor model in Go with the Ergo framework — where actors came from, why they beat shared-state threading, and a worked prime-factoring example.