MinIO

MinIO is the data and memory foundation for enterprise AI.

[MinIO @Minio]

Repeated context means repeated computation, wasting valuable GPU cycles that could generate new tokens.

MinIO MemKV is the shared context layer that helps you put your GPUs to work on what matters. 💪

[MinIO @Minio]

MinIO and @nvidia combine high-performance data technologies with accelerated computing to maximize GPU performance, eliminate redundant computation, and give AI agents the memory they need to operate at scale.

See the technology powering the next era of enterprise AI at #SC26.

📅: https://t.co/LkI8UPO8Ic

[MinIO @Minio]

London calling. Your data can stay put. 🇬🇧

We're heading to #DataAIWorldTour London to show how AIStor connects @databricks to live, on-prem Iceberg and Delta tables through native OpenSharing. No replication. No additional pipelines.

📍 Nov. 11 | Excel London https://t.co/AYlbFjAflZ

[MinIO @Minio]

How do you connect the dots between what AI agents know, what they remember, and what they can do?

Conversations, decisions, and context hold valuable knowledge that agents need across tasks and sessions. AIStor Memory brings it all together.

[MinIO @Minio]

Performance at scale starts with the right technology.

At #SC26, MinIO and @MicronTech are joining forces to demonstrate how high-performance flash and AIStor unlock greater throughput, lower CPU overhead, and improved efficiency for demanding AI workloads.

See it in action: https://t.co/LpGG6tARll

[MinIO @Minio]

Your GPUs have better things to do than wait for data. ⏳

As AI workloads scale, slow data pipelines can leave powerful GPUs sitting idle.

AIStor delivers the performance and scalability to keep data flowing and AI workloads moving.

[MinIO @Minio]

Cache hits are only part of the equation. What matters is their impact on production AI.

⬇️ Lower P99 latency
⬆️ Higher concurrency
💸 Better GPU economics

In Part 3 of our prompt caching series, we break down how to evaluate shared context memory and measure its impact on inference performance at scale. https://t.co/FsOnu3Lx0x

[MinIO @Minio]

AI agents are getting smarter. But where does the knowledge go? Co-founder and co-CEO @abperiasamy explores this question for @FastCompany.

Organizational memory is the next competitive advantage in enterprise AI. Learn why 👇 https://t.co/178FtphPZj

[MinIO @Minio]

MinIO is headed to #SC26 ⭐

We're proud to be a sponsor and showcase how AIStor delivers the performance and scalability needed to power enterprise AI at scale.

Connect with our team and explore the future of AI infrastructure. https://t.co/MY5MxMWzc2

[MinIO @Minio]

Modern AI and analytics demand more from enterprise data infrastructure.

MinIO AIStor is architected to meet those demands with a unified platform for memory, tables, and objects, native support for open table formats, and cloud-native scalability.

One data foundation. Built for what's next. https://t.co/QlybUhgSJD

[MinIO @Minio]

Follow the KV.

The runtime finds a reusable prefix. The hottest KV stays close to the GPU. Reusable state can move into shared context memory. And when that context is needed again, the serving stack restores it instead of rebuilding it.

This is how prompt caching works across an inference fleet, and where MemKV fits in the path. https://t.co/WajuTiSwBz

[MinIO @Minio]

Our engineering team is pushing the boundaries of what's possible, even as development timelines accelerate.

Co-founder Garima Kapoor explains what's driving this acceleration and what it means for the future of software development. ⬇️

https://t.co/qmNrUa5Tgc

[MinIO @Minio]

As enterprise AI scales, fragmented systems and growing data volumes strain infrastructure.

🎥 CTO Ugur Tigli joined SDxCentral to discuss how a unified data foundation can overcome these challenges and support AI at scale. https://t.co/XOKZbUdSFQ

[MinIO @Minio]

MinIO is headed to ODSC AI West 2026 on Oct. 27-29 🌁 https://t.co/JAHR8E7c6V

From connecting enterprise data to analytics to building persistent memory for AI agents, we're showcasing how MinIO delivers the data and memory foundation for AI at scale alongside our partners at @databricks and @nvidia.

Find us at Booth #7 to meet the team and explore what's possible with AIStor.

[MinIO @Minio]

Skip the demo. Build it yourself. 🛠️

In these technical workshops, you'll get hands-on experience with AIStor + Databricks, connecting on-premises data to analytics without moving or replicating it.

Two hours. Your own lab environment. A working, secure table share.

📅 November 12 or 18 | Limited to 40 participants per session

Register now: https://t.co/Hm5xXwzgDh

[MinIO @Minio]

Agentic AI is changing what GPUs need from memory infrastructure.

Using @NVIDIA Nemotron 3 Ultra on NVIDIA H200 GPUs, our engineering team tested what happens when context can persist beyond GPU memory, and what that means as concurrent agentic workloads scale.

The results point to a new way to think about context memory for enterprise AI. https://t.co/3uJntYLaHd

[MinIO @Minio]

What if security agents could reason across relationships without moving data?

@puppyquery + AIStor enables graph queries and SQL analytics on the same data, giving AI agents grounded context without a separate graph database.

➡️ Here's a tutorial: https://t.co/UVjGQIiiJy

[MinIO @Minio]

3️⃣ steps. No data movement.

AIStor connects on-premises data directly to @databricks with native Table Sharing, keeping a single copy of your data in place and ready to query.

Go deeper in our upcoming training webinar to move from setup to query.

🔗: https://t.co/smZ76zDYHm

[MinIO @Minio]

Congratulations to AB and all the innovators recognized by https://t.co/ahrrWheldl for advancing the future of AI! https://t.co/GqBP3mM4Do

[MinIO @Minio]

Congratulations to MinIO Co-founder and CEO @abperiasamy on being named to @h2oai's 2026 AI 100 list! 🎉

A well-deserved recognition of his vision and leadership in building the high-performance data infrastructure enterprises rely on to power AI at scale.