MinIO delivers Exascale Object Store for AI Data, Agentic Computing, and Analytics with unmatched enterprise performance.

Joined February 2015
1,694 Photos and videos
Pinned Tweet
May 12
MinIO MemKV is a new class of infrastructure. ✨ For years, we’ve focused on the data foundation for AI. Today, we’re extending that foundation into the inference layer, where efficiency and performance define success. What does this mean for the stack and the future of AI? Co-CEO and co-founder Garima Kapoor explains.
2
3
223
MinIO retweeted
Great conversations happen when infrastructure leaders come together to solve the challenges of scaling AI. Excited to see @Solidigm and @MinIO on stage together at AI Infrastructure Field Day. #AIIFD5 techfieldday.com/appearance/…
2
7
532
MinIO retweeted
Modern object storage and high-density SSDs are helping organizations build scalable, efficient AI factories. Looking forward to sharing insights alongside the @MinIO team! techfieldday.com/appearance/…
2
5
272
MinIO retweeted
Announcing OpenSharing, a new open standard for sharing data and AI assets across platforms and organizations. Five years ago, we pioneered open data sharing with Delta Sharing, the most widely adopted open protocol for secure zero-copy data sharing - used by thousands of partners and customers. Today, we're excited to announce its evolution to OpenSharing: The first open, vendor-neutral protocol for sharing AI assets, including agent skills, AI models, and unstructured data - in collaboration with partners including @OpenAI, @SAP, @LSEGplc, @stripe, @TheTradeDesk, @Minio, @AmadeusITGroup, @Atlassian, and more. Enterprises can now use OpenSharing to share AI Assets, on-premises assets, as well as share structured and unstructured data in all formats. Hosted by The @linuxfoundation, OpenSharing creates an open foundation for data and AI collaboration in the agentic era. databricks.com/company/newsr…
1
11
73
4,025
Jun 12
Women don't just participate in innovation, they lead it. Congratulations to our co-founder and co-CEO, Garima Kapoor, for being named one of the 100 Women in AI by XFactor Ventures and Flybridge, and to all the remarkable women shaping every corner of the AI ecosystem. 🎉 bit.ly/4ec4Y8a
99
Jun 11
The countdown to #DataAISummit is on. Together, MinIO and @databricks are helping organizations break down data silos with open, high-performance data infrastructure that makes it easier to access, share, and activate data for analytics and AI. If you're headed to SF next week, stop by booth #527! The future of AI starts with the right data foundation. Let's talk about building both. bit.ly/4bFPwhP
1
102
Jun 10
Data that cannot move needs an architecture that never asks it to. Enter AIStor Table Sharing. AIStor Table Sharing connects on-premises and hybrid storage platforms to the Databricks Data Intelligence Platform via the OpenSharing protocol. Dive into the architecture and why it matters for our customers with Field Architect Dwight Evers. bit.ly/3Q5TXx3
4
179
Jun 10
The most valuable enterprise data is often the hardest to reach. That's why we're excited to join the @databricks Software-Defined Storage (SDS) Ecosystem as a founding partner. MinIO AIStor natively implements OpenSharing at the storage layer, enabling Databricks to access on-premises Apache Iceberg and Delta tables through Unity Catalog without replication, migration, or additional data services. bit.ly/4v5ukvw
1
3
156
Jun 10
We're proud to support OpenSharing, a new open standard for sharing data and AI assets across platforms and organizations from @Databricks, as the only GA solution. With native OpenSharing support in MinIO AIStor, organizations can unlock data across on-premises and private cloud environments while maintaining control, governance, and performance. bit.ly/43n78g6
1
112
Jun 8
MinIO officially joins ClickHouse House Mates, a partner community and program built to help customers find trusted integrations and certified experts in their region. 🤝 Our inclusion shows that AIStor is a high-performance, exascale object store built for AI-era workloads and is the best fit for on-prem ClickHouse in production. We're proud to be a trusted and validated partner. bit.ly/4xb2O0Z
1
139
Jun 8
We're a proud sponsor of @HPE Discover 2026 in Las Vegas! We're looking forward to connecting with customers, partners, and the broader HPE community to discuss what's next for AI, analytics, and cloud-native infrastructure. If you're attending, stop by booth #2006 and say hello to the team. 👋 bit.ly/4xgQSek
3
118
Jun 4
AI factories run on data. Together with @solidigm and @intel, we put a ~24PB cluster to the test, achieving up to 268 GiB/s throughput in just 8 nodes. This integrated stack delivers the throughput and efficiency modern AI workloads demand. Density without compromise. Performance at scale. The data infrastructure for modern AI factories. Read more on our blog. bit.ly/4fs3t7U
492
Jun 3
Autonomous driving runs on data. Lots of it. A leading North American automobile manufacturer built a global AI data platform with MinIO AIStor to support autonomous driving, simulation, and analytics at an extraordinary scale. The result: a high-performance, cost-efficient foundation for AI that can grow with the business. 👉 Find out how they did it: bit.ly/4g06b4F
2
117
Jun 1
MinIO AIStor and MemKV now support NVIDIA Vera BlueField-4 STX, delivering a secure AI data path from persistent S3 object storage to in-context GPU memory. Together, MinIO and @nvidia help enterprises build secure-by-design AI factories where every byte moving through the AI data pipeline is protected, governed, and delivered without compromise. Learn more about the announcement from #GTCTapiei at #COMPUTEX. bit.ly/3PWxeDn
2
3
154
May 28
If the recompute tax is the problem, why hasn’t anyone solved it yet? Because AI infrastructure was never designed to preserve context at GPU scale. So every follow-up request forces the system to rebuild the state repeatedly, wasting expensive GPU cycles. MinIO MemKV creates space in GPU memory, offloads the KV cache, and instantly recalls context when it’s needed again. The result is less recompute, more decoding, and higher effective GPU utilization. 👇 See how MemKV helps eliminate the recompute tax.
1
133
May 28
We're excited to join the global data and AI community at @databricks #DataAISummit. From sessions and demos to technical deep dives and meetups, it's going to be an incredible week on the future of AI, analytics, and data architectures. 🚀 Stay tuned for a full lineup of activities. databricks.com/dataaisummit
1
2
113
May 26
📣 This week at @starburstdata AI Datanova: CTO Ugur Tigli is helping financial services build AI-ready data infrastructures. From governance and federated data models to scaling AI across complex, regulated environments, this panel discussion, alongside Citizens Financial and TIAA, will offer insights into what it takes to move AI from experimentation to enterprise-scale deployment. 👉 See the full agenda: bit.ly/4wKa6J8
2
109
May 22
Federal agencies are in a new phase of AI adoption, where infrastructure decisions will define long-term success. As VP of Public Sector Deep Grewal writes for @FederalNewsNet, scalable federal AI demands modern architectures built for resilience, portability, and operational independence across hybrid environments. The path to trusted AI starts with the foundation. bit.ly/4f1apZr
332
May 21
Most vendors approach “context memory” by adapting general-purpose caching systems originally designed for file servers. We’re not most vendors. MinIO MemKV is the first purpose-built context memory store for AI inference. It’s built differently and delivering results 🧵
1
2
218
May 21
Runs as one ARM64-native binary embedded in the NVIDIA STX, not a separate cluster connected over the network.
1
93