HN thread debates value of agent sandboxes and rival tools
4 Sep 20 9:31 PM · 5d ago · 1 post · 8 comments · 2 sources · development 4 of 4
Commenters compare AX to existing frameworks such as Mastra and an internal tool called clrk, question whether isolated sandboxes are worth the complexity, and some dismiss the product page as unclear about its purpose.
“Nobody has a use for this, and anybody who can look at this website and work out what it's for is kidding themselves.”
weedfroglozengeGoogle Developer of AXblazarquasar HN submitterMond_ HN commenterdilyevsky HN commenter, builder of a similar internal toolbriga HN commenter
The whole story articlespostscomments the bright band is this development · numbered dots are the others · click one to jump
What people said 24 voices · best of 42 · verbatim
-
From what I've seen, the vast majority of agent sandboxes with funding aren't for developers to use when coding, but for production applications that want to have LLMs do work. It's just a different model - APIs are better than a great terminal experience for a coding harness.I've been working on https://lullabot.github.io/sandbar/latest/ which…
-
N
AX – Google’s Open Agentic Orchestrator Link: https:// agentexecutor.io Comments: https:// news.ycombinator.com/item?id=4 9780797
-
I'm working on something in the "cloud VMs for agents" space[1], so I have some battle scars and opinions!IMO, you want the flexibility to create either: (a) permanent devbox VMs, and (b) per-task VMsAgent sandbox platforms tend to be tuned for the latter, which sometimes involves VMM hackery for fast boot, snapshotting VM filesystem and RAM…
-
N
AX – Google’s Open Agentic Orchestrator: https:// agentexecutor.io Discussion: http:// news.ycombinator.com/item?id=4 9780797
-
So 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…
-
For my workflow I need both, a permanent-ish VM and emphemeral sandboxes. Both have their place and pros and cons.VMs are better for personal assistant work, GUI clicktesting, investigating bugs in your personal dogfooding dev instance and anything you haven‘t yet made repeatable and fast to set up.Sandboxes are better when you need resource…
-
Yes perhaps easy refers to when actually using AX as a platform for deploying and managing agents, not actually installing and managing AX itself. I think it's awesome they targeted kubernetes but it's not easy from a human perspective. However with documentation and an AI assistant working with Kubernetes is so nice. I have worked with all the…
-
> Task declares the container image and command, compute requests and limits, environment variables [...] Declares listeners the task exposes and an egress allowlist of hosts and ports the sandbox may reach. Use it to restrict an agent to, say, your LLM provider and your Git host.I'm planning to buy a whole linux mini-PC to run my agents/code…
-
Yeah, my grandmother also did something on this https://github.com/nillebco/vardaEssentially there is no out of the box solution about orchestrating agents and increasing LLMs sandboxing. That's why everyone and their grandmother are re-inventing the wheel.At the same time, it's an incredibly complicated problem, with a variable perimeter (OS…
-
Could someone explain to me what the general workflow is now that people are converging to? I haven't really been catching up with the AI ecosystem but I was looking into agent sandboxes and VM's recently and there's a ton of these startups and tools now. Is giving the agent a temporary scratchbox really that valuable?I've been still just like…
-
Basically everyone has a sandbox of some sort to run agents inside. Everyone has a registry of some sort for tools. Everyone has a way of running agents inside a sandbox and giving it some tools.Now the stuff people are coming up with is: how do you do authorization in this model? do you need a full sandbox all the time or can it be a workflow?…
-
I never quite understood why agents should be treated as anything but normal software engineering. "Just" build a normal service and add an async call to some agentic framework, then parse the results. There is no need to "flip" this system and have the agent BE the process and invent a whole new ecosystem to manage the complexity that this flip…
-
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…
-
We have built similar abstractions directly on top of Kubernetes [1]I was looking at this project a couple of months ago, and I did not understand why not use Kubernetes instead of rebuilding the abstractions. The reason is that Kubernetes already provides other abstractions to run services and batch job, gang scheduling, gpu and other…
-
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…
-
I don't think there is really any convergence going on. The agentic ecosystem is continuing to multiply on a daily basis and everyone and their grandma has written a new agent framework--people are stepping over each other to get these new projects out the door.That said, I think Google's ADK ecosystem and this new AX platform is promising--I…
-
I am confused by this. The UX of the CLI is almost identical to kubectl, but it doesn't seem to actually be built on K8s CRDs. There's a backend that runs on k8s, but doesn't seem natively integrated.Because it's using `ax apple` instead of `kubectl apply` you can't use tools like argocd for managing resources.It's built on agent substrate which…
-
I have no idea, I just live in my terminal at this point, on linux. Don't use Visual Studio or Jetbrains products anymore at all. I use visual studio code to view the occasional diff and run sql queries. Other than that, zero desktop apps, just terminal & cli tooling. Its great! I have about 20 terminals open at any given time though. I have no…
-
The general workflow I have seen for non-technical people building software is something like:- Do multiple tasks in the same context window / session, conflate different changes into the same prompt- Repo mixed with old markdown files from previous tasks, excel and word docs and 300 playwright screenshots- 5 tools all calling each other, test and…
-
I am wondering how this is related to https://agent-sandbox.sigs.k8s.io/ ? Since there is also
-
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…
-
> Drawing on agentic runtime research from Google DeepMind alongside deep experience in large-scale isolation, resumption, and scheduling, AX is being built as an open, declarative control plane purpose-built...The project seems like an open-source initiative born out of the experience of some Googlers but not being used at Google. So, the title…
-
I've been using https://github.com/mastra-ai/mastra which is pretty similar but has workflow visibility and a number of templates.For a generic swarm, workflows aren't too useful which does away with the visibility, so I may give this a try instead.
-
> What's wrong with that?Nothing at all. You'll know when you've outgrown it.> what the general workflow is now that people are converging to?Graph-based workflows where agents pick up work as it becomes available, structured output, while you manage the work queue and outcomes. Maybe? IDK really, it's all moving quite fast.
All 4 developments of Google Engineers' Open 'Agent Executor' Orchestrator Surges… →
Hacker NewsMastodonNewswires