OpenInfer, an AI Agent Engine with a cross-hardware OS, democratizing real-time intelligence, efficiency, and privacyopeninfer.io San Francisco, CA, USAJoined November 2024
Two years ago we built @openInfer around CPUs being central to agentic AI.
Everyone said we were wrong.
NVIDIA just shipped "the CPU for agents."
@intel's CEO called the CPU "the indispensable foundation of the AI era."
CPU:GPU ratios moving from 1:8 → 1:1.
The ground moved.
openinfer.io/news/2026-06-0…#openinfer#inference#heterogenous
60 days. Three deals. One bet: agentic inference will not run on one chip.
→ Feb 24: Intel Xeon + SambaNova
→ Mar 13: NVIDIA Rubin + Groq LPX (disaggregated inference)
→ Last week: Meta + millions of AWS Graviton CPU cores
Three stacks. Three processor mixes. One pattern.
━━━━━━━━━━
NVIDIA said it bluntly: "prefill and decode place different demands on hardware." Layer agentic behavior on top (tool calls, planning, retrieval, verification, multi-agent coordination) and the demands shift again on every step.
The future of AI infrastructure isn't more GPUs. It's more kinds of compute, coordinated across a topology.
━━━━━━━━━━
Three things change once multi-processor agentic inference is the default:
→ Accelerator door opens. Every credible silicon player gets a seat.
→ Tail latency becomes an architectural decision, not a tuning problem.
→ Scalability shifts axis. Agentic inference > model inference.
━━━━━━━━━━
At @openInfer we call this vertical disaggregation. First proof point: Intel Xeon CPU + NVIDIA GPU. +50% capacity, zero additional GPUs.
The harder problem is dynamic workloads, multiple models, across aggregated hardware.
That's what agentic inference actually is:
multiple SLAs, multiple models, dynamic behavior changes, served by multiple compute topologies.
→ Intel: CPU + accelerator layer
→ NVIDIA: GPU + LPU layer
→ Meta: CPU layer
→ Next race: the orchestration layer that knits them together
Sources:
Intel + SambaNova: newsroom.intel.com/data-center/in…
NVIDIA Groq 3 LPX: developer.nvidia.com/blog/inside-nv…
Meta + AWS Graviton: aboutamazon.com/news/aws/meta-…
Vertical Disaggregation (OpenInfer): openinfer.io/news/2026-04-2…#A
We just published how we unlocked +50% inference capacity on a 27B model — no new GPUs, no new nodes, at a fraction of the cost.
Turns out the CPU sitting next to your GPU isn't dead weight. We just had to stop treating it like it was.
Full breakdown ↓
Come and Try out our Beta (FREE): OpenClaws Restriction is Fixed
We are opening up our Beta (openinfer.io/beta) hosting openClaw background task on lower end, complex cloud topologies, demonstrating value of an inference system built the agentic world.
We have building the infrastructure for Agentic flow in mind. What we saw with @AnthropicAI announcement is a demonstration that agents need to be treated differently than conversational ai
@OpenAI tripling revenue. @AnthropicAI at $14B ARR. @nvidia at $130B.
Who's paying? Enterprises.
But change is coming — cheaper AI, new competitors, margin compression. Some companies will get devalued. Others will explode.
That's exactly why we built @openInfer
Featured in @CIOonlinecio.com/article/413767…
The "wow" phase of AI is over. We’ve entered the era of 𝗣𝗿𝗮𝗰𝘁𝗶𝗰𝗮𝗹 𝗔𝗱𝗼𝗽𝘁𝗶𝗼𝗻.
I’m excited to share my latest interview with @TechNewsWorld. Special thanks to @jpmello for the great conversation on @OpenAI's 2026 strategy.
Key focuses: 𝗔𝗜 𝗮𝘀 𝗜𝗻𝗳𝗿𝗮𝘀𝘁𝗿𝘂𝗰𝘁𝘂𝗿𝗲: Moving from novelty to a foundational operating layer. 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗙𝘂𝘁𝘂𝗿𝗲: AI agents solving real-world problems in health and science. 𝗗𝗲𝗹𝗶𝘃𝗲𝗿𝗶𝗻𝗴 𝗥𝗢𝗜: Scaling to meet global enterprise needs.
Now, the real work of transforming how the world functions begins—driven by the need for transformational infrastructure and @openInfer 𝗯𝘂𝗶𝗹𝗱𝗶𝗻𝗴 𝗶𝗻𝗳𝗿𝗮 to support this new era.
Full interview: technewsworld.com/story/openai-c…#OpenAI#openinfer#AI#TechTrends#openinfer@TechNewsWorld
𝗧𝗵𝗲 𝗻𝗲𝘅𝘁 𝗔𝗜 𝗰𝗼𝗺𝗽𝘂𝘁𝗲 𝘀𝗵𝗶𝗳𝘁 𝗶𝘀 𝗶𝗻𝗳𝗲𝗿𝗲𝗻𝗰𝗲.
Edge data is exploding.
Inference must move to data.
This requires a ground-up system, not a model upgrade.
NVIDIA + Groq is an early signal.
2026 is when inference infrastructure becomes the battleground.
🎙️ New Podcast Episode
I joined The Software Leaders UNCENSORED Podcast to talk about why the future of AI is at the edge and how we are building OpenInfer to make reliable, secure, and energy efficient physical AI possible.
Here is what I cover:
• How my experience across @Meta , @Google , and @Roblox shaped @openInfer's edge first mission
• Why AI needs to run where data is created and how our unified stack makes that real
• How we push innovation through custom inference and system mementos to bring datacenter level AI to the edge
• What I learned from 250 enterprise leaders on why most AI projects fail
• How to stay ahead in a field that changes every 90 days
Full episode link in the comments.
#AI#openinfer#edgeai#inference
Imagine a world physical AIs could recall the past, could come together and build a stronger reasoning.
To make inference happen on edge, Memory Constraints needs to be addressed as a system architecture (HW+SW).
@openinfer is sharing a glimpse of what is possible if an edge system is designed to recall the past.
Check us out openinfer.io/demos/mementos/#openinfer#physicalai#inference#edgeai
Bringing inference to edge requires massive innovation around Memory system.
Restructuring how inference on edge should be run, we are sharing a capability to remove the lack of meaningful on-device memory.
Our latest release lets models hold persistent context, reason over
Bringing inference to edge requires massive innovation around Memory system.
Restructuring how inference on edge should be run, we are sharing a capability to remove the lack of meaningful on-device memory.
Our latest release lets models hold persistent context, reason over larger spans, and collaborate intelligently. all running locally on the OpenInfer engine.
This is how we break past edge memory limits.
🔗 openinfer.io/demos/mementos/#edgeAi#openinfer#mementos#inference
Here’s how it works:
1️⃣ Submit a one-pager idea by Oct 3, 2025 → [email protected]
2️⃣ We review & select top concepts
3️⃣ Finalists present live in San Mateo
4️⃣ Winners pitch to top VCs + access OpenInfer early!
161 Followers 484 FollowingLiterally just Cars, Hybrid Cloud, Modern Apps, K8s, OSS & memes. internet plumber: @dtrio_ // Principal Alchemist: https://t.co/c3jTkhsO0L Ex - @Microsoft
488 Followers 2K FollowingPaediatrics. Genetics. Economics. Pop health. Rare Insights. Truth not Truthiness. Don't believe the hype... @VUWUpdates2go @Flinders @unimelb_mpghss
131K Followers 554 FollowingTech writer @logrocket, @sitepointdotcom and @refine_dev 📚
Built DevTunes FM (1.8M+ listens) and DevQuizzes (900K+ answers) 🚀
290 Followers 449 Following"Own the Narrative"
Curating 1,000+ domains that define the machine-identity layer of AI - where compute, inference, and trust converge.
#OwntheNarrative
2K Followers 3K FollowingInvesting in advanced technologies for people and planet @kintsugiad 🏞️ Previously Co-founder of PredictionIO 🐸 (Acquired by Salesforce) and Ph.D. @UCLCS 🖥
2K Followers 2K FollowingI am a freelance writer specializing in business and technology subjects, including consumer electronics, business computing and cyber security.
110 Followers 2K FollowingLady im besten Alter; mit starker Leidenschaft für Higheels und gepflegte Füsse. DM für mehr,,,
#Feet #Highheels #Footfetish #Hotmom #Nails
112 Followers 1K FollowingTurn your documents into a private AI knowledge base with AskTuring. SOC 2 secure, zero training on your data. Join the waitlist today 👇
4K Followers 2K FollowingJConnelly is a leading integrated communications and digital media agency where your brand is understood, enhanced & fiercely protected.
2K Followers 2K FollowingI am a freelance writer specializing in business and technology subjects, including consumer electronics, business computing and cyber security.
143 Followers 168 FollowingCeo / Cofounder @openInfer
Bringing Data Center-Scale AI to Edge ㅣ previously Sr. Director of eng at @roblox , @meta, earlier @google x
4.7M Followers 458 FollowingCutting-edge research, news, commentary, and visuals from the Science family of journals. Follow @NewsfromScience for stories from our News team.
31 Followers 44 FollowingBuilding out cool tech at stealth startup and angel investing. Opinions my own. Ex GAF (Google/Apple/FB). OSes, indoor GPS, Pixel Buds, VR, cloud, AI, do it all
1.6M Followers 1K FollowingCo-Founder of Coursera; Stanford CS adjunct faculty. Former head of Baidu AI Group/Google Brain. #ai #machinelearning, #deeplearning #MOOCs
4.9M Followers 4 FollowingOpenAI’s mission is to ensure that artificial general intelligence benefits all of humanity. We’re hiring: https://t.co/dJGr6LgzPA
1.5M Followers 278 FollowingThe engine room of @Google. Building AI safely and responsibly to solve the world’s most complex problems. Join us: https://t.co/jUHQA27iBL
808K Followers 322 FollowingTogether with the AI community, we are pushing the boundaries of what’s possible through open science to create a more connected world.
1.4M Followers 2 FollowingWe're an AI safety and research company that builds reliable, interpretable, and steerable AI systems. Talk to our AI assistant @claudeai on https://t.co/FhDI3KQh0n.