OpenAI is doing the Joel Spolsky move, commoditize the layer above yours. Google did it with Kubernetes back when GCP was losing on infra. If they don't put a spec out, every orchestrator gets built around MCP or A2A by default and OpenAI is the third wheel. The spec is free, the runtime is where the money is..
My team has already been keeping significant context in tickets (sessions are just too ephemeral). I‘ve been envisioning this as the next step.
This might just make me take another look at Codex, though I’m sure it’ll be adaptable to other harnesses.
Has anyone tried implementing this spec for themselves?