At #KubeCon NA, our Founder & CEO Yodar Shafrir sat down with @theCUBE Research team to talk about how AI agents are changing the economics of cloud infrastructure.
Watch the interview and read the article here: https://t.co/qOu7IPNiMI
@pnashawaty@knightrm@SiliconANGLE
Catch @scaleops_ai at @awscloud re:Invent 2026 in Las Vegas, Nov 30 to Dec 4.
Here is where to find us:
📍 Live demos at Booth 268: autonomous compute orchestration for enterprise AI, with zero configuration
📅 Mon, Nov 30, 8:30 to 9:30 a.m. PT: Agentic AI Needs Agentic Infrastructure: Autonomy on Amazon EKS
⭐ Landing in Vegas? Keep your eyes up
Last week on the #KubeCon NA keynote stage, our Founder & CEO Yodar Shafrir took a deep dive into our solution for agentic workloads, and the ‘swap’ feature that moves idle agent memory out of RAM to a fast storage tier and back on demand, reducing consumption by as much as 90%.
Watch the keynote here: https://t.co/Ow56OefGlG
Yesterday at #KubeCon, our founder & CEO @ShafrirYodar presented “Autonomous Orchestration for AI Infrastructure.”
He closed by unveiling memory Swap for agents, which can save up to 90% of cloud spend.
Missed it? Watch the recording below!
Day one at #KubeCon NA is done and we kicked it off the ScaleOps way! Visitors lit up at our agentic workloads demo.
Today we go bigger for day 2! Keynote, Wed Nov 11: our CEO will present “Autonomous Orchestration for AI infrastructure.”
Catch us at booth 123! @CloudNativeFdn
SPONSOR NEWS: Save the date: catch @scaleops_AI at #KubeCon NA! Live demo Tue, Nov 10 at 10:30am, then CEO Yodar Shafrir keynotes Wed, Nov 11 at 9:36am with “Context Unlocks Autonomous AI Infrastructure.” Stop by Booth #123 at the Salt Palace. #CloudNativeCon
A 100% vLLM prefix cache hit rate can sit on a KV cache that is mostly memory nobody will hit again. Hit rate counts matches, not GiB that get reused.
Read how the memory splits: https://t.co/4ap8WEUKmS
Many thanks to diamond sponsor @scaleops_ai for supporting #KubeCon + #CloudNativeCon North America, Nov 9-12 in Salt Lake City! Learn how teams are operating agent workloads and running efficient infrastructure at scale. Learn more: https://t.co/qAOhEhoi9K
@scaleops_ai is heading to #KubeCon NA 2026, Nov 9-12, Salt Lake City.
Booth 123, Salt Palace. Autonomous compute orchestration for enterprise AI, live on a real cluster, zero config.
Book a meeting: https://t.co/cdqlLK2bX0
@CloudNativeFdn
@OutSystems cut compute costs 43%. The project was never about cost. Crash loops in, zero YAML changes and zero tickets out. How the platform team did it:
Go Autonomous. Read the case study here: https://t.co/vcOj1CppNd
@scaleops_ai is presenting at @kingfisherplc's Cloud and Data Meetup Kraków on this Wednesday.
We will cover why the usual fixes for Kubernetes resources stall before they reach production, and what it takes for orchestration to act autonomously in production instead: in real time, with guardrails, across applications, agents, and models on CPU, GPU, and memory.
- October 7, 18:00 | HEVRE, Meiselsa 18, Kraków
- Free to attend. Registration is required, and entry closes at 18:00.
- Reserve your seat: https://t.co/RMKkJQm6wS
Armis (from @ServiceNow) cut Kubernetes vCPU allocation by 30% across every cluster after deploying ScaleOps, our AI infrastructure platform.
Static resource requests set once and forgotten are gone. So is manual tuning. What's left is autonomous right-sizing.
🎬 Watch the case study here: https://t.co/KmJ2jexISG
Kubernetes 1.37 makes the DRA bridge for https://t.co/TyxcUhQ7ZM requests GA. On a real T4 node, the vendor driver produced GPU device classes but zero ResourceSlices ever appeared, and no slice means nothing for a claim to bind to.
https://t.co/fdwUEhgZqR
Kubernetes 1.37 resize preemption bypasses node affinity. I reproduced it on kubeadm v1.37.0: 3 pods evicted for a resize, then the resize refused on the same affinity the eviction skipped. Alpha, gated off, with a per-node off switch.