This actually huge.
can now get your hermes to spin up codex sandboxes natively within your file system, and it orchestrate.
This will allow massive parallel for optimal compute power, as you can stay on simple machine for the core runtime.
One Hermes’ could power n sandboxes running PRs.
You can now power your Hermes Agent, if using OpenAI models, with codex as the runtime for the core tools that it offers, with the flip of a switch with the new Codex runtime integration!