Full video - piped.video/FHp8dbUcu0A?si=L2j4…

The checkout failed. Inventory was fine. Where did it break? In this simulated OpenObserve demo, the trace leads to payment.charge and its injected timeout. Follow the request, then inspect the failing span. #OpenTelemetry

video piped.video/FHp8dbUcu0A?si=VqPT…

A storage benchmark can be accurate and still be easy to misread. OpenObserve’s published run reports 118 GB of compressed data, or 211 GB of actual disk use including indexing. Elasticsearch used 375 GB. But the systems accepted different amounts of data: 100% of documents for OpenObserve and 38% for Elasticsearch in that mapping configuration. Before comparing the headline numbers, check what each includes and how much data actually made it in. Which benchmark detail do you check first? #Observability #OpenObserve #CloudNative

Tokyo, here we come 🇯🇵 AGNTCon + MCPCon Japan 2026 📅 Sept 10–11 Building AI agents, MCP servers/clients or agentic AI infrastructure? This is one to join. 🎟 ¥44,000 JPY Code: KUBESIMPLIFY #AGNTCon #MCPCon #AgenticAI

Kubesimplify is teaming up with ContainerDays & AI Context Singapore as a media partner this year. October 27–28, Suntec Singapore. Two days that are actually about the work , production Kubernetes, platform engineering, AI infrastructure, and where agentic tooling and MCP are heading next. 60+ sessions from people who are building this stuff, not just talking about it. If you're in cloud native or AI infra, this is the one to be at in Singapore this year. Check the Link below👇

etcd runs your entire cluster and most people treat it as a black box. 7 things worth knowing, one per tweet:

🚨 Big one for the community! PyTorch Conference North America 2026 📅 Oct 20–21 | 📍 San Jose ✅ 7 technical tracks ✅ 3 co-located events ✅ Demos, posters & networking Learn from Meta, UC Berkeley, Pinterest & more on Cudagraphs, TorchDynamo & multi-node training. 🎟️ 40% OFF with code: KUBESIMPLIFY 🔗 Registration link below 👇 #PyTorch #ML #AI

KubeCon + CloudNativeCon North America 2026 is coming. November 9 to 12, Salt Lake City. CNCF's flagship conference brings together adopters and technologists from across the open source and cloud native world, all working to advance cloud native computing. What's inside: - Expert-led talks - Latest innovations from leading vendors - 11 CNCF-hosted co-located events - Parties and unmatched networking with TeamCloudNative - Swags Community discount: 20% off current pricing. Code: KUBESIMPLIFY20 Registration Link pinned below👇

Session 1 of the KubeSimplify Book Club is done. We're reading Inference Engineering by Philip Kiely and this week covered the Preface, Chapter 0, and Chapter 1. Chapter 0: - open models (Hugging Face, Nvidia) are closing the gap with closed frontier models, a big reason inference engineering is hot in 2026 - local inference means running models on your own hardware - every decision comes down to latency, availability, and cost - the pipeline: training, learning, inferencing, serving on the ground: teams renting GPU racks from providers like NeevCloud, enthusiasts buying DGX Spark and Nvidia GPUs Chapter 1: - model weights are layer 1, inference runtime is layer 2 - speculative decoding to speed up generation - the sumo wrestler vs swimmer analogy for throughput vs latency tradeoff - metrics to know: TTFT, TPS, P90 - tensor parallelism to scale across GPUs Recording is up, link below. Next session Friday 8:30 PM IST with Saiyam.

🦚 Happy Janmashtami from KubeSimplify! Today, we celebrate Lord Krishna and the values he represents -- wisdom, compassion, courage and doing what is right. 🙏 May this Janmashtami bring peace, happiness, prosperity and positivity to you and your loved ones.💙 Enjoy the festivities, spend time with family & friends, and make the most of the day! ✨ And if you have some time tonight, join Saiyam for the first session of our AI Inference Engineering Book Club. 📖 🕣 8:30 PM IST 🔗 Register now, link below👇 Once again, Happy Janmashtami! 🦚💙

Something new is happening at KubeSimplify. Saiyam Pathak is kicking off something he has wanted to do for a long time: The KubeSimplify Book Club. Another way for the community to learn together through reading, discussion, demos, and hands-on experiments. The book we’ll cover today is: Inference Engineering by Philip Kiely And it feels like the perfect place to begin. Inference today is not just about calling an API. There is a lot to understand, and the idea behind the book club is simple: Meet today(4th Sept 2026) , around 8:30 PM IST The free book link and the live session link are in the comments.

8 physical GPUs → 80 schedulable GPU units. Sounds like Kubernetes magically created 72 extra GPUs. It didn't. We configured HAMi to let workloads share the same physical GPUs through logical scheduling slots. The interesting part? Free slots don't mean unlimited GPU memory. We pushed it with a 90GB pod request and Kubernetes said: CardInsufficientMemory Full blog link below 👇

Saiyam contributed the kiac quick installer guide to OpenChoreo. It's now merged. One curl command creates a Deployment, Service and HTTPRoute/Gateway from 20-30 lines of intent. Fully wired. Full video linked below👇

A crate with 245 million downloads became a malware dropper this week. Full anatomy, tweet by tweet🧵

🚨News from KubeSimplify Book Club. After six sessions deep into the Google SRE Book -- covering the production environment, tenets, and embracing risk -- we are taking a break from SRE and switching gears entirely. This Friday, Saiyam takes over the session and we are opening a brand new book. AI Inference Engineering by Philip Kiely. It focuses on the discipline of running generative AI models reliably, efficiently, and at scale in production. Inference engineers work across the entire technology stack from CUDA to Kubernetes to serve models faster, cheaper and with higher uptime. The timing for this could not be more relevant. The Book is free to download. All levels are welcome. Join us this Friday at 8:30 PM IST on our Discord server. All links pinned below.

YAML hell: ingress here, Helm there, five environments quietly drifting apart. Saiyam's new video breaks down OpenChoreo a CNCF Sandbox IDP where devs ship ~30 lines of YAML and the platform handles CI, GitOps, RBAC and observability underneath. Full video linked below👇

Your local LLM benchmark says thousands of tokens/sec. Then you run it. Feels slow. every request has two phases Prefill (reads your prompt) and Decode (writes the answer). They behave nothing alike. Prefill → parallel. Fast. Decode → one token at a time, each depending on the last. Slow, by nature. That's the distinction behind almost every confusing benchmark number. It's 1 of 50+ terms in our Local LLM Glossary. Link below #LocalLLM #AIInfrastructure

KubeSimplify is a Media Partner for ContainerDays x AI Context Hamburg 2026! 📅 Sep 2–4 | 📍 Hamburg 🇩🇪 Cloud-native + agentic AI, focused on what actually works in production Kubernetes, MCP, multi-agent systems, observability & governance. 🚢 Plus, an offsite stage aboard the historic MS Bleichen. Register now, link below 👇

Happy Raksha Bandhan from Kubesimplify. Our goal stays the same: empowering techies through education and open source, free content for everyone, and a community where people help each other grow. Grateful for another year of building this together.

Kubesimplify Book Club : Session 6. Tomorrow, 8 PM IST. Picking up where we left off in Chapter 3: Embracing Risk. → Consumer services: Why Google Apps for Work gets 99.9% but YouTube 2006 got less. Why a privacy leak means you take the service down, but a failed profile picture is just a bug. → Infrastructure: Bigtable can't be ultra-reliable for everyone. Low-latency users want empty queues; MapReduce users want full queues. The fix: service tiers at 10–50% of the cost. → Cost math: 99.9% → 99.99% on a $1M service earns $900. If it costs more, it's a bad investment. → Error budgets: The politics killer. Dev wants velocity, SRE wants stability. The budget is the neutral referee. When it runs low, dev teams self-police. Every Friday, book-club channel 8pm IST, Join our discord(link below) See you there! #SRE #ErrorBudgets #DevOps #PlatformEngineering #GoogleSRE #KubeSimplify

Something breaks. And as an on-call engineer you head to your machine, straight into incident response mode. Copy the pod name from Slack. Search logs in another tab. Check metrics on a dashboard. Open a ticket somewhere else. Pull up a runbook and hope it's still accurate. None of that is SRE work. It's glue work. Saiyam put NudgeBee v1.4.0 to test, a unified AIOps platform: AI-SRE, AI-FinOps, AI-K8sOps, and Agentic Automation. Self-hosted end to end, control plane, cluster, even the model. Full breakdown, link in comments 👇

ContainerDays x AI Context Hamburg 2026 📅 September 2-4 | 📍Hamburg Two co-located conferences at Schuppen 52, a historic warehouse on the Hamburg waterfront. ContainerDays -- Kubernetes, containers, platform engineering AI Context Hamburg -- agentic AI in production: MCP, multi-agent orchestration, governance, evaluation, observability CTOs, Heads of AI, platform leads and enterprise architects, sessions led by practitioners sharing what they've actually shipped Bonus: an offsite session aboard the MS Bleichen, a historic ship on the waterfront Register using our media partner link👇 tickets.loovent.com/cdshambu…

Your API gateway doesn't speak the agent language. Built for one request → one backend → one response. It can't parse MCP JSON-RPC. Can't hold long-lived sessions And treats tool descriptions as to be blindly trusted metadata. That gap helped MCP rack up 40+ CVEs in 2026. Tool poisoning, shadowing, rug-pulls, all walking straight past REST-only proxies. @agentgateway aims to close it. Open source. Rust-built. Under Linux Foundation. - One proxy for HTTP/gRPC, LLM traffic, MCP federation & A2A. - Protocol-aware routing. - Session-level CEL RBAC. - SSE state management. - Tool virtualization per client. - JWT/OAuth/TLS/rate limits/OTel out of the box. Agents make probabilistic decisions and invoke tools dynamically. Securing that needs a gateway that speaks the protocol natively. If agents are in your production traffic, worth checking out #MCP #A2A #AgentSecurity #Kubernetes #CloudNative #OpenSource

Kubesimplify is heading to Cloud Native Summit Kerala 2026 — and this time with two sessions on stage. Saloni is joining an amazing keynote panel, for "Future of Infrastructure: The Role of Humans," alongside: Ram Faseela Nabarun Pal A conversation about automation, AI, open source and where human judgment still fits in as infrastructure gets smarter. Later in the day, she's back with her own session: "Your Base Image Is Production: Hardening Kubernetes Supply Chains from Layer One" a look at supply chain security starting from the one layer most teams overlook. @cnskerala 2026 is shaping up to be the biggest cloud native gathering Kerala has hosted -- 800+ engineers, 40+ speakers, 3 parallel tracks (Cloud Native · Operate & Observe · What's Next), covering everything from Kubernetes at production scale and service mesh to AI agents on Kubernetes, GPU orchestration and zero-trust security. 📅 Saturday, 22 August 2026 📍 Le Méridien, Kochi Register: cnskerala.in #CloudNative #Kubernetes #CNCF #KubernetesKerala #KubernetesCommunity #CNSKerala2026

Want to attend AI Infra Summit 2026 for FREE? 8,000+ attendees. 400+ speakers. 100 FREE Expo tickets. As the official media partner, KubeSimplify is giving away 100 Expo tickets exclusively for our community. 📍 Santa Clara, CA 📅 Sept 15–17 Need a VIP or full-access pass? Use “KUBE15” for 15% OFF. Links below. Register now! #AIInfraSummit #AI #GenAI #Kubernetes #CloudNative

📚 Kubesimplify Book Club — Session 5 Recap This week we started "Embracing Risk" from Google's SRE book, and it already flipped a lot of assumptions about reliability on their head.

Growing together! Happy independence day to all.. thank you for amazing love and support!

SRE Book Club : Session 5. Tonight, 8 PM IST. Chapter 3: Embracing Risk. → 99.999% costs 100x more than 99.99%. Your users can't tell. → SLOs are ceilings, not floors. Exceeding them is waste, not a win. → Error budgets replace "ship vs. don't ship" debates with math. → Google doesn't measure uptime. They measure aggregate request success rate. This is the chapter that separates SRE from ops. Join live → discord.gg/EXUuCjdz?event=15… #SRE #ErrorBudgets #PlatformEngineering #DevOps #KubeSimplify

Traffic crossing clusters in Istio still gets authenticated. Here's how the east-west gateway + sidecar handle auth for every cross-cluster request, using service account tokens under the hood. Full workshop: piped.video/live/FwXF-ICECLc

KCD Gujarat 2026 full schedule is now LIVE 8 dedicated tracks covering everything from Platform Engineering and Cloud Native Experience to AI Inference + Agentic systems, Security, Observability, and beyond. Whether you're building platforms, shipping apps, or securing infrastructure, there's a track built for you. 🗓️ Full schedule: kcdgujarat.com/schedule 📅 19 September 2026 📍 Ahmedabad 🎟️ Grab your spot: kcdgujarat.com/register

One label is all it takes. Istio auto-injects the Envoy sidecar into every pod in a namespace. Watch the pod count go from 1/1 to 2/2 in real time. Full workshop👇

Missed our live Service Mesh 101 workshop? The recording is now up. Total hands-on with Istio on Kubernetes, covering the architecture, traffic management, security, multi-cluster networking and observability, all with live demos and slides. If you've wanted to actually understand where Istio fits and what you can build with it, this is worth the watch. Check it out now:  piped.video/watch?v=FwXF-ICE…

We are happy to share that Saloni is speaking at Cloud Native Summit Kerala 2026, Joining an amazing panel to discuss "Future of Infrastructure: The Role of Humans." Alongside, Ram Iyengar - Chief Evangelist, The Linux Foundation Faseela K - CNCF TOC, Cloud Native Ericsson Nabarun Pal - Principal Engineer, Broadcom An honest conversation about automation, AI, open source and the human judgment that still sits at the center of it all. If you're planning to be in Kerala for Cloud Native Summit and care about where this field is heading, this is a room to be in. 📅 Saturday, 22 August 2026 📍 Le Méridien, Kochi Register now👇 #CloudNative #Kubernetes #CNCF #KubernetesKerala #KubernetesCommunity

NVIDIA dropped Nemotron 3.5 Lightning yesterday. Saiyam already pulled it on his DGX Spark and benchmarked it. The headline: 108 tok/s decode via vLLM + NVFP4, ~2,600 tok/s prefill, and a single agent step that took 26s on Qwen3.5 35B? Done in 5.9s here. But first if your Ollama is older than v0.32.9, you'll hit a 412 error and wonder why. So here's the fix, the exact vLLM serve command, raw API logs and why raw tok/s isn't the real story for agent workloads. All Measured. Link below👇

🚨 @WeMakeDevs is hosting another BIG hackathon: Into the Scrape-Verse ONLINE 🚨 🔗 Register now: forms.gle/FY3UAHqs7Gw1hDLE6 Why should you participate? > 🖥️ Win an NVIDIA DGX Spark AI Personal Supercomputer worth $5,000 > 🏆 Apple iPad for every winning team member > 🎁 Iron Man MK5 Helmet for one lucky registration > ⌨️ Keychron Keyboard for every winning team member Using Bright Data Scraper Studio, you'll learn how to combine AI with web data and build applications that can understand, extract, and act on information from virtually any website. You can participate solo or in a team of 4.

KubeSimplify is a proud media partner for ContainerDays x AI Context Hamburg 2026 📅 Sept 2-4 | 📍 Hamburg Europe's biggest cloud-native + agentic AI event, all in one. Real practitioners. Real production lessons. Zero vendor fluff. - Kubernetes at scale - AI from pilot to production - MCP, orchestration, governance, observability Bonus stage on a historic ship on the Hamburg waterfront Seats are filling up fast. Don't miss it🎟️ Register with our partner link👇 tickets.loovent.com/cdshambu…

Book Club update. 3 sessions into the Google SRE Book: S1-S2: Chapter 1. Sysadmin model, SRE's founding, error budgets, on-call, change mgmt S3: Chapter 2 start. Datacenter topology, failure domains, Borg to Kubernetes, storage stack Session 4 tonight: finishing Chapter 2. Jupiter, B4, GSLB, Chubby and the Shakespeare walkthrough. Join us. Links below!

🚨 This weekend @WeMakeDevs is hosting: The Zerops Challenge 🚨 It's a 48 hours solo buildathon and the idea is simple - build cool projects and deploy it on Zerops. Amazing prizes up for grabs * Apple MacBook for the strongest overall project * Logitech MX Master 3s for the best social post * $5,000 in Zerops credits Zerops handles the runtimes, databases, and infra so you can spend the weekend on your product instead of your deployment pipeline. Push your code, and it takes care of the rest. Register using their website: bit.ly/45rJLmJ

🚨Live Workshop: Service Mesh 101 with Istio Going live August 10, 5:00 PM. Join in as Sayed Imran, Golden Kubestronaut, takes us from zero to production-grade Istio on Kubernetes. Traffic management, mTLS, observability, troubleshooting, multi-cluster networking. All live, with Q&A. Basic Kubernetes knowledge is enough. No Istio experience needed. This is a hands-on live session. Register now and set a reminder👇 streamyard.com/watch/f6QXYFa… #Istio #Kubernetes #ServiceMesh #DevOps #CloudNative

SBOMs in 2026: past the buzzword, before the value. Here's the honest state of SBOMs on Kubernetes.

🚨 Happening now at KubeCon + CloudNativeCon Japan! Join Saiyam , Faseela , Hidetsugu and Darshan to discuss why sustainability in cloud native needs to move beyond good intentions and into real action. 🕓 Now Live 📍 Room 411+412 (4F) • Track 2 If you’re at KubeCon, don’t miss this session🌱 #KubeCon #CloudNative #CNCF #Sustainability #GreenSoftware

In 2 hours we go live. KubeSimplify Book Club – Session 2. 8PM IST. Discord. Tonight , the core tenets of SRE. Error budgets. Monitoring. Emergency response. Change management. Capacity planning. Link down below 👇 See you at 8.

Session 2 of KubeSimplify Book Club is tomorrow. 24th July. 8PM IST. Discord. Last week we covered why SRE exists and how Google thinks about production. Tomorrow we go deeper -- into the actual tenets that every SRE team at Google operates by. Error budgets. Monitoring strategy. Emergency response. Change management. Capacity planning. The frameworks behind systems that serve billions of users. If you are in the SRE space or trying to break into it -- this is exactly the material that separates people who understand reliability from people who just talk about it. Free. All levels welcome. No experience needed. Join the Discord from the link below. Head to #book-club. See you tomorrow at 8PM IST.

Confidential Containers is now a CNCF incubating project. Big milestone for confidential computing in cloud native.🧵

We had fun interacting with the Cloud Native community at the @cncfchd × @AgenticAIFdn Meetup and the answers were as diverse as the ecosystem itself! Open source isn’t just about code it’s about the people, ideas and conversations that bring communities together. A huge thank you to everyone who stopped by and shared their favourite project with us. Now it’s your turn! What’s YOUR favourite open source project? Drop it in the comments below. 👇 #OpenSource #CloudNative #CNCGChandigarh #AgenticAIFoundation #Kubernetes

⚽ Extra Time Added -- Savings Now Through July 31 @linuxfoundation's World Cup-themed promotion just got extended. More time to train like a champion and certify like a pro. 🥅40% off Bundles (incl. Kubestronaut Bundles) -- Code: JULY26BUNKS 🥅35% off Individual Courses & Exams -- Code: JULY26CCKS Score big before the deadline. Now valid through July 31, 2026.

In 2 hours we go live. KubeSimplify Book Club -- Session 1. Google SRE Book. How Google thinks about production. The SRE mindset from the people who built it. All levels welcome. No experience needed. Discord link down below 👇 See you at 8.

Community events like @cncfchd do not run on good intentions alone. They run on sponsors who show up and back the people building this ecosystem. As community partner, we were glad to see Vultr power the CNCG and @AgenticAIFdn Chandigarh Meetup on July 18, 2026. The room will definitely make the most of it, with conversations ranging from sandboxing AI agents safely on Kubernetes to scaling RAG pipelines in production, plenty of hands-on demos and honest lessons from people running these systems for real. None of it happens without the right support behind it. Thank you @Vultr , for investing in the cloud native community in Chandigarh. Spots are limited and filling up fast. Grab yours before they're gone. Link down below👇

Kicking off tomorrow. 8PM IST. KubeSimplify Book Club : Session 1. We are breaking down how Google thinks about production systems through the eyes of an SRE. If you are in the SRE space or trying to get into it -- this is exactly where you want to be tomorrow night. All levels welcome. No experience needed. Join our Discord -- link down below👇 See you tomorrow. ☸️