alt Hacker NewsSo on one hand the page says
> We want to make dealing with agentic infrastructure easier so you can focus on your work. AX is designed with an uncompromising focus on ergonomics, rapid iteration, and joyful workflows for both application developers and AI researchers.
On the the other hand, the readme quickstart section says
> You need a Kubernetes cluster, ko (brew install ko), a container registry your cluster can pull from, and a reachable Agent Substrate Control API (in-cluster default: api.ate-system.svc.cluster.local:443).
Call me old-fashioned but I don't find this "easier". Maybe it's easier in the same way that Kubernetes itself is easier than managing VMs and container deployments at massive scale without such a tool. But there's a vast chasm between what this tool is being sold as and what it actually is.
Replies
If you are approaching anything looking like an enterprise environment, you are likely to have Kubernetes nearby. ko is a weird requirement. ax requires agent substrate, so it makes sense that it's needed. Agent Substrate also has experimental support in kagent, so it makes sense that it is growing.
I don't really like the oversubscription of agent pods though, as you can no longer trust the k8s pod identity as being from a singular workload. Haven't seen a solution to this for ax yet and it is a barrier to adoption for us.
It is easier in that if you have infrastructure already, it's trivial to add this on top. The primitives look also very familiar.
As with everything in software engineering, any average dev can fire up a few containers with Docker, but running anything in a real environment takes a whole team of people who actually understand the platforms involved in order to deliver a fully functional service, hopefully via properly designed code (TF) for ease of reusability. Most devs simply don't care to think about that part, and then throw it over the fence for "someone else" to deal with. Just as long as they can say "DONE!" (I created a thing!), that's all that matters.
Classic AI solution, you do the hardwork so that you can chat to an agent to do the easy part.
I agree, also the problem is the substrate is still in beta. So this is a beta on another beta: it seems not fully mature.
I'd prefer a K8s Operator or plugin (like Istio) to get all the pack.
Obligatory https://youtu.be/3t6L-FlfeaI
Google operates at such a scale with a wide surface area of serious production considerations that even “ergonomic” solutions internally feel extremely heavyweight externally.
Source: I’m an Xoogler
Easier from enterprise perspective.
Heavily biased a kube admin but make kube clusters is easy now - its literally one command (aws eks create-cluster/gcp ... something something haven't done it in awhile after doing it multiple times a day in a past life) - I think its more familiarity with the tools that is the challenge - creating a vm is also easy if you know how, brew/apt/yum install is easy if you know how, setup.exe is easy etc)