AX by Google
Ranked 7 of 26 agent orchestrators by recommenders
Google's open platform for scaling agentic applications on Kubernetes and deploying them to others' compute. Critics find it heavyweight, hard to use and immature.
Google's open platform for scaling agentic applications on Kubernetes and deploying them to others' compute. Critics find it heavyweight, hard to use and immature.
41 people gave an opinion
- recommend it
- 15
- criticize it
- 26
- approval share
- 37%
Recommended in 4 of 13 months
- November 2025: recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 15 people recommend itNeeds 10 or more, met.
- 0.5 recommenders for every criticNeeds 2 to 1 or better, not met.
- Recommended in 4 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Scales agents on Kubernetes
“I think it's awesome they targeted kubernetes but it's not easy from a human perspective.”
Comment from 23 Sep 2026 in “AX – Google’s Open Agentic Orchestrator” “two agent runtimes designed for scaling out, that are both kind of neat”
Comment from 13 Jun 2026 in “A low-carbon computing platform from your retired phones” “basically virtual threads for kubernetes”
Comment from 20 Sep 2026 in “AX – Google’s Open Agentic Orchestrator” Runs agents on others' compute
“Today, it's extremely hard to deliver large agentic applications to someone else's compute”
Comment from 22 Sep 2026 in “AX – Google’s Open Agentic Orchestrator” “if you have infrastructure already, it's trivial to add this on top”
Comment from 21 Sep 2026 in “AX – Google’s Open Agentic Orchestrator”
What people warn about
Each mark is one comment
Overbuilt and heavyweight for most
“It looks great from a security standpoint, but it also feels like overkill.”
Comment from 21 Sep 2026 in “AX – Google’s Open Agentic Orchestrator” “even “ergonomic” solutions internally feel extremely heavyweight externally”
Comment from 21 Sep 2026 in “AX – Google’s Open Agentic Orchestrator” “building an incompatible monolith with the kitchen sink included”
Comment from 21 Sep 2026 in “AX – Google’s Open Agentic Orchestrator” Hard to use, poor docs
“I think it's awesome they targeted kubernetes but it's not easy from a human perspective.”
Comment from 23 Sep 2026 in “AX – Google’s Open Agentic Orchestrator” “Nobody has a use for this, and anybody who can look at this website and work out what it's for is kidding themselves.”
Comment from 21 Sep 2026 in “AX – Google’s Open Agentic Orchestrator” “It doesn't explain anything and it just seems to be a collection of random commands that someone ran to test”
Comment from 21 Sep 2026 in “AX – Google’s Open Agentic Orchestrator” - Comment from 21 Sep 2026 in “AX – Google’s Open Agentic Orchestrator”
- Comment from 21 Sep 2026 in “AX – Google’s Open Agentic Orchestrator”
Oversold; little new versus others
“there's a vast chasm between what this tool is being sold as and what it actually is”
Comment from 21 Sep 2026 in “AX – Google’s Open Agentic Orchestrator” “I don't see a meaningful difference to the 100s of other 'agentic frameworks'”
Comment from 20 Sep 2026 in “AX – Google’s Open Agentic Orchestrator” Immature beta, may be abandoned
“create a big launch for promo, then maintain it briefly then slowly let it die”
Comment from 20 Sep 2026 in “AX – Google’s Open Agentic Orchestrator” “So this is a beta on another beta: it seems not fully mature.”
Comment from 21 Sep 2026 in “AX – Google’s Open Agentic Orchestrator”
Other agent orchestrators people recommend
The four most recommended other agent orchestrators, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Gas Town | 95 | 212 | 31% | 10 | 1 mo3 owners | — |
| Conductor | 58 | 25 | 70% | 11 | — | Approved |
| Superset | 33 | 16 | 67% | 8 | 2 mo4 owners | Approved |
| Scion by Google | 28 | 32 | 47% | 8 | — | — |
| AX by GoogleThis page | 15 | 26 | 37% | 4 | — | — |
What people said
40 of the 46 comments that mention it, newest first. Each links to the original comment.
“I think it's awesome they targeted kubernetes but it's not easy from a human perspective.”
“Today, it's extremely hard to deliver large agentic applications to someone else's compute”
“They will sunset this in 6 months. Dont bother”
“It doesn't explain anything and it just seems to be a collection of random commands that someone ran to test”
“I have an application usecase where this will be very helpful indeed.”
“So this is a beta on another beta: it seems not fully mature.”
“It's completely opaque what this tool is.”
“ko is a weird requirement. ax requires agent substrate, so it makes sense that it's needed.”
“Classic AI solution, you do the hardwork so that you can chat to an agent to do the easy part.”
“even “ergonomic” solutions internally feel extremely heavyweight externally”
“Easy as in "Google cloud console interface" easy”
“if you have infrastructure already, it's trivial to add this on top”
“Personally I would stay away from them as far as possible.”
“there's a vast chasm between what this tool is being sold as and what it actually is”
“must look cool for people who want to solve every problem with k8s”
“It can set-up a Python 3 environment.”
“From their own example "Setting up a Python 3 environment" is best it can do.”
“I hope something with a decent dev UX will appear one day. AX definitely is NOT.”
“Remember kids, a model is not a model.”
“Kubernetes for agents. I guess all roads lead to complex YAML.”
“Restoring a harness in 500ms is really fast, much faster than naively creating a new job”
“It looks great from a security standpoint, but it also feels like overkill.”
“Unnecessary complexity packaged as product!”
“this promotion packet fodder for anything important is a fool”
“It doesn't look like Google's AX is quite the plug-and-play fit for running agents on a computer you own”
“By contrast, "low opinion" means build something new, from scratch, atop this brand new platform.”
“Nobody has a use for this, and anybody who can look at this website and work out what it's for is kidding themselves.”
“this new AX platform is promising--I would expect Google to maintain this and other tooling around this for years to come”
“building an incompatible monolith with the kitchen sink included”
“I wouldn't expect this to have GDM leadership backing”
“Almost all of the things it offers should be table stakes for everywhere we run not only agents but most software.”
“Overly complex; yaml files, heavy framework.”
“I don't see a meaningful difference to the 100s of other 'agentic frameworks'”
“create a big launch for promo, then maintain it briefly then slowly let it die”
“basically virtual threads for kubernetes”
“it feels so much less integrative, is such it's own thing.”
“two agent runtimes designed for scaling out, that are both kind of neat”
“if you're in the typescript world”
“use Meta's AX optimisation framework to finetuning the settings”
“Just use something like DSPy/Ax and optimize your module for any given LLM”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.