Lately it supports running agents in Podman containers. It's also possible to independently update Agent harness versions without updating the CLI tool.
One of the next items on the roadmap is tidying up the architecture to clearly define what's in the core of that framework and what's plugged into the framework on top of it - kind of a plugin system.
Plugins may bundle settings such as what commands need to be run when building the container images, startup commands that need to run when starting the containers or the definition of information that should be forwarded from the host into agents' containers (environment variables, networking settings, etc.).
So far, I am hoping for (more) external contributions as well as someone who is willing to share ideas or talk about the concepts around that framework. :-)