MinIO (@Minio) header
MinIO (@Minio) profile picture

MinIO is the data and memory foundation for enterprise AI.

Palo Alto, CA
Joined February 2015
Pinned Tweet
Today marks 2️⃣ years of AIStor and the general availability of AIStor Memory. With objects, tables, and persistent agent memory on one governed foundation, we're helping enterprises unlock more value from their data and the knowledge AI agents generate. min.io/press/minio-marks-two…
1
2
189
This week at #SC26 reinforced where enterprise AI is headed: faster infrastructure, persistent memory, and greater efficiency at scale. Together with partners across the ecosystem, we're advancing the technology needed to power the next generation of AI workloads.
154
Advancing enterprise security and observability requires collaboration across the industry. 🤝 Chief Corporate Development Officer Ran Kurup shares how our partnership with @datadoghq is bringing greater visibility, scalability, and data control to enterprise AI. bit.ly/4eM7tix
1
1
189
Moving more data doesn’t have to mean adding more infrastructure.​ Together with @Minio, we tested an all-flash #AI data lake using MinIO AIStor, internode RDMA and Micron 6600 ION SSDs. RDMA delivered 36% higher peak read throughput while reducing CPU utilization and power consumption.​ More performance, same infrastructure. Learn more:​ bit.ly/3VzQ0TW ​​#AIInfrastructure #DataCenter
7
11
1
102
5,351
More AIStor demos. More conversations. More #SC26! ⚡ Day two is all about our partnership with @nvidia, advancing GPU performance and persistent agent memory for enterprise AI. Join us at Booth #1016 for a MinIO + NVIDIA happy hour from 2–4 PM. 🍹
2
2
187
MinIO and @datadoghq are joining forces to power the security and observability lakehouse for enterprise AI. Through this strategic partnership, AIStor becomes the first high-performance, on-premises lakehouse certified for Datadog Bring Your Own Cloud (BYOC). Together, we're enabling enterprises to retain and analyze every log at scale while maintaining complete control over their data. bit.ly/4eLxWN3
1
2
1
744
Day one of #SC26 ✅ MinIO + @MicronTech are advancing AI performance with high-performance flash and AIStor for greater throughput and efficiency. Thanks for stopping by for Memory Match, photos, and great conversations! 📸 📍 See you at Booth #1016!
1
3
288
With @Equinix and @databricks, we're tackling one of enterprise AI's biggest challenges: unlocking critical data for analytics while preserving privacy, sovereignty, and control. On the agenda at #DataAIWorldTour NYC: 🔗 Zero-copy data access through OpenSharing 🌐 Private global connectivity ⚙️ Production-ready deployments bit.ly/49280JG
1
188
AI is everything. We're at #SC26 this week, showcasing how AIStor delivers the performance, scale, and persistent memory needed to power production AI. Learn more at Booth #1016. bit.ly/4zlLTto
1
3
220
Enterprise AI is complex enough. Your data infrastructure shouldn't add to it. AIStor simplifies operations with an open, unified architecture that reduces costs and works with the tools enterprises already use. Less complexity. More value from your AI investments. 💡
1
178
MinIO and @databricks are bringing enterprise data and analytics closer together. 🤝 🎥 From the floor at #DataAIWorldTour London, we spoke with Field Architect Jonny McCormick about enabling live access to on-premises data from Databricks without moving or duplicating it.
2
241
Your @Supercomputing lineup is here! 📋 AIStor powers the next generation of AI factories, intelligent agents, and AI-ready lakehouses with the speed, scale, and efficiency that production AI demands. Learn how to bring these capabilities into your own environment at #SC26. bit.ly/4zlLTto
3
208
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. 💪
1
191
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. 📅: min.io/events/lp/minio-sc26
1
1
219
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 bit.ly/4eILsRN
2
260
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.
2
188
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: bit.ly/4zlLTto
6
220
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.
1
136
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. bit.ly/4jV1QSy
1
1
177
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 👇 bit.ly/4sE33Qt
179