Available now in public preview on Zilliz Cloud, Vector Lakebase keeps production vector search at its core and adds shared lake-native storage and on-demand compute — bringing real-time serving, interactive discovery, and batch analytics onto one data foundation.

REDWOOD CITY, Calif., June 10, 2026 /PRNewswire/ -- Zilliz, the company behind Milvus, the world's most widely adopted open-source vector database, today announced the public preview of Zilliz Vector Lakebase, a major Zilliz Cloud release that pairs the production vector database with a shared, lake-native data foundation.

Vector Lakebase keeps Zilliz Cloud's real-time vector search at the core — the engine Zillow, OpenEvidence, Exa, Filevine, MiniMax, and more than 10,000 enterprises and AI teams already rely on — and extends it with three new ways to operate on the same data: interactive discovery, large-scale batch analytics, and search directly on external data lakes. The result is a single data foundation in which every workload runs against a single logical copy of the data, with on-demand and batch jobs billed only when compute is active.

"Production vector search is and will remain at the heart of what Zilliz does — it's why thousands of teams choose Milvus and Zilliz Cloud, and it's getting faster and more cost-efficient every release," said Charles Xie, Founder and CEO of Zilliz. "Vector Lakebase is what we believe comes next: one data foundation where the same vectors can serve a production query, anchor a discovery session, and power a multi-petabyte training-data pipeline — without copies, migration, or a parallel stack."

Why a Single Data Foundation Matters

AI systems are no longer a single-query retrieval problem. They run as a continuous loop — serve, learn from feedback, mine and prepare better data, then serve again — and each turn typically requires separate systems for serving, exploration, and large-scale processing. Moving billions of vectors between those systems can take days. The cost and complexity are so high that many teams skip the loop altogether, leaving valuable data retrievable but never improved.

Vector Lakebase closes that gap with a zero-copy semantic data plane on shared lake-native storage: real-time serving, interactive discovery, and batch analytics all run against one logical copy of the data, scaling from gigabytes to petabytes.

"Teams asked for a way to keep their data in one place and run very different workloads against it — from real-time agent memory to overnight semantic deduplication," said Robert Guo, VP of Product at Zilliz and one of the architects behind Milvus. "Vector Lakebase delivers that through a unified storage layer on Vortex, tiered serving for the production path, and on-demand compute for everything else."

Five Capabilities on One Foundation

• Tiered Real-Time Serving. Three production tiers tuned for different workloads: Performance-Optimized (1,000+ QPS, single-digit-millisecond latency, in-memory); Capacity-Optimized (100–500 QPS, sub-100ms latency, memory + NVMe); and Tiered-Storage (10–50 QPS, ~100ms latency, spanning memory, NVMe, and object storage at significantly lower cost). All tiers default to 95–98% recall, tunable to 99%+, backed by Zilliz Cloud's 99.99% uptime SLA and Global Cluster cross-region high availability.
• On-Demand Search. Pay-as-you-go compute for workloads where infrastructure sits idle most of the time, billed directly for object storage and compute rather than serverless markups. In Zilliz's internal benchmark on one billion 768-dimension vectors with 10 hours of monthly active compute, On-Demand Search totaled $318 versus $4,937 for a comparable serverless path — roughly 1/15 the cost.
• External Data Lake Search. A zero-copy External Collection mode that adds state-of-the-art indexing and full-spectrum search directly to existing Lance, Iceberg, Parquet, and Vortex tables, with incremental sync on refresh. Source data stays where it lives.
• Full-Spectrum AI Search. Search across vectors (dense and sparse), text, JSON, and geospatial data, with hybrid retrieval, BM25, regex, multi-vector and iterative search, and multi-path retrieval. Results can be reranked with Cohere, Voyage AI, RRF, and weighted/boost/decay strategies.
• Unified Lake-Native Storage. Shared storage for serving and analytics built on Vortex, an open columnar format designed for faster, cheaper random reads than Lance and Parquet, paired with object-storage-aware indexes (vector, BM25, JSON) that cut read amplification by over 90%. A 100-million-row schema backfill typically completes in single-digit minutes — without disrupting active query traffic.

Together, these capabilities let AI teams consolidate what previously required parallel always-on serving clusters and separate batch systems onto one platform — with consistent indexes, versioned data, and compute that scales to zero between jobs.

Availability

Zilliz Vector Lakebase is available now in public preview on Zilliz Cloud, alongside Serverless, Dedicated, and BYOC deployment options across more than 30 regions on AWS, Google Cloud, and Microsoft Azure. New work email signups receive $100 in free credits at zilliz.com. Teams running serving, discovery, and analytics on separate stacks can contact the Zilliz team for a tailored walkthrough.

About Zilliz

Zilliz is a leading AI data infrastructure company and the creator of Milvus, the world's most widely adopted open-source vector database, with 44,000+ GitHub stars and over 100 million Docker pulls. Zilliz helps enterprises and AI startups make their unstructured data searchable, analyzable, and governable — turning text, images, audio, video, and more into a strategic asset for production AI.

Zilliz's technology centers on Milvus and Zilliz Cloud. Milvus is an open-source vector database purpose-built for 100-billion-scale vector search. Zilliz Cloud extends that foundation into a fully managed Vector Lakebase platform, combining the high-throughput, low-latency serving capabilities of vector databases with the openness, scalability, and economics of multimodal data lakes. Zilliz powers more than 10,000 enterprises and AI-native startups worldwide, including MiniMax, OpenEvidence, Filevine, Exa, Salesforce, and Read AI.

Headquartered in Redwood Shores, California, Zilliz is backed by leading investors, including Aramco's Prosperity 7 Ventures, Temasek's Pavilion Capital, Hillhouse Capital, 5Y Capital, Yunqi Partners, and Trustbridge Partners. Learn more at Zilliz.com.

New Global Cluster and Global Endpoint capabilities deliver automated failover with near-zero downtime for enterprise AI applications

REDWOOD CITY, Calif., March 27, 2026 /PRNewswire/ -- Zilliz, the company behind Milvus, the world's most widely adopted open-source vector database, today announced native cross-region disaster recovery for Zilliz Cloud, making it the only vector database to offer automated cross-region failover with near-zero data loss and sub-60-second recovery times.

Recent high-profile cloud outages — including simultaneous AWS region failures in the Middle East, a 14.5-hour Azure outage, and cascading infrastructure incidents costing Fortune 500 companies billions — have exposed a critical gap in AI infrastructure resilience. With nearly 60% of employees now relying on AI-powered workflows daily, region-level failures no longer cause gradual slowdowns; they trigger immediate productivity cliffs across the enterprise.

"Cloud regions will fail — that's not a prediction, it's an operational certainty. What matters is whether your AI infrastructure can recover in seconds rather than hours. We built cross-region disaster recovery natively into Zilliz Cloud so that enterprises never have to choose between the performance of vector search and the resilience their applications demand." said Charles Xie, Founder and CEO at Zilliz.

Why Cross-Region Disaster Recovery Matters for AI

Vector databases power critical enterprise AI workloads — from RAG pipelines and semantic search to recommendation engines and AI agents. Unlike stateless model inference, vector indexes containing hundreds of millions of vectors can take 18+ hours to rebuild, making traditional disaster recovery approaches impractical. Zilliz Cloud's new capabilities address this with three complementary solutions:

• Global Cluster: Real-time Change Data Capture (CDC) replication between primary and secondary clusters in different regions enables planned switchovers with zero data loss and automatic failover in under 60 seconds.
• Global Endpoint: A single connection endpoint with SRV DNS-based routing automatically reroutes application traffic during failover — requiring no code changes, connection string updates, or application restarts.
• Cross-Region Backup: Cost-effective backup replication to target regions with configurable retention policies, enabling recovery from any backup point for workloads where data durability is the priority.

Beyond disaster recovery, Global Cluster also enables latency optimization by placing replicas closer to end users, zero-downtime region migrations, and compliance with geographic data residency requirements.

Now Available

Cross-region disaster recovery capabilities are now available on Zilliz Cloud dedicated clusters across AWS, GCP, and Azure. Existing customers can activate Global Cluster and Global Endpoint from the Zilliz Cloud console. New users can create a free account with $100 in credits to get started. For enterprise deployments, connect with the Zilliz team.

About Zilliz

Zilliz is the company behind Milvus, the world's most widely adopted open-source vector database. Zilliz Cloud brings that performance to production with a fully managed, cloud-native platform built for scalable, low-latency vector search and hybrid retrieval. It supports billion-scale workloads with sub-10ms latency, auto-scaling, and optimized indexes for GenAI use cases like semantic search and RAG.

Zilliz is built to make AI not just possible — but practical. With a focus on performance and cost-efficiency, it helps engineering teams move from prototype to production without overprovisioning or complex infrastructure. Over 10,000 organizations worldwide rely on Zilliz to build intelligent applications at scale.

Headquartered in Redwood Shores, California, Zilliz is backed by leading investors, including Aramco's Prosperity 7 Ventures, Temasek's Pavilion Capital, Hillhouse Capital, 5Y Capital, Yunqi Partners, Trustbridge Partners, and others. Learn more at Zilliz.com.

New CMEK capability gives regulated enterprises full control over encryption keys for AI-scale vector workloads

REDWOOD CITY, Calif., March 20, 2026 /PRNewswire/ -- Zilliz, the company behind Milvus, the world's most widely adopted open-source vector database, today announced the general availability of Customer-Managed Encryption Keys (CMEK) on Zilliz Cloud. The new capability allows enterprises to retain full ownership of their encryption keys, delivering true data sovereignty for AI workloads in regulated industries.

As enterprises embed AI into mission-critical workflows, the sensitivity of the underlying data—customer records, medical images, financial transactions—demands security controls that go beyond standard encryption at rest. Regulatory frameworks such as GDPR, HIPAA, PCI-DSS, and SOC 2 increasingly require organizations to demonstrate exclusive control over their encryption keys, not just the data they protect. For vector database deployments—where embeddings are derived from highly sensitive assets—this requirement is especially acute.

"Security teams in regulated industries don't just want encryption—they want proof that no one else, including their database vendor, can access their data. CMEK gives enterprises the strongest form of data sovereignty available in a managed service, removing one of the last barriers to deploying AI at scale in healthcare, financial services, and government," said Charles Xie, Founder and CEO at Zilliz.

Why CMEK Matters for Enterprise AI

CMEK on Zilliz Cloud separates key ownership from data processing, ensuring that Zilliz never possesses or accesses customer encryption keys. Key benefits include:

• True Segregation of Duties: Zilliz processes data while the customer retains exclusive control over encryption keys, creating the clean separation auditors and compliance teams require.
• Instant Revocability: Disabling a key in AWS KMS immediately renders all associated cluster data cryptographically inaccessible—no vendor coordination needed.
• Unified Audit Trails: Every key access event is logged in AWS CloudTrail, integrating directly with existing enterprise security monitoring infrastructure.

Setup takes minutes through the Zilliz Cloud console, with auto-generated IAM policies and support for zero-downtime key rotation.

Now Available

CMEK is generally available today for Dedicated clusters on the Zilliz Cloud Business-Critical plan, starting with AWS. To get started, visit the Zilliz Cloud console or connect with the Zilliz team to discuss your deployment requirements.

About Zilliz

Zilliz is the company behind Milvus, the world's most widely adopted open-source vector database. Zilliz Cloud brings that performance to production with a fully managed, cloud-native platform built for scalable, low-latency vector search and hybrid retrieval. It supports billion-scale workloads with sub-10ms latency, auto-scaling, and optimized indexes for GenAI use cases like semantic search and RAG.

Zilliz is built to make AI not just possible—but practical. With a focus on performance and cost-efficiency, it helps engineering teams move from prototype to production without overprovisioning or complex infrastructure. Over 10,000 organizations worldwide rely on Zilliz to build intelligent applications at scale.

Headquartered in Redwood Shores, California, Zilliz is backed by leading investors, including Aramco's Prosperity 7 Ventures, Temasek's Pavilion Capital, Hillhouse Capital, 5Y Capital, Yunqi Partners, Trustbridge Partners, and others. Learn more at Zilliz.com.

New open-source library lets developers give any AI agent long-term memory that humans can read, edit, and trust—extracted from OpenClaw's viral memory system and powered by the Milvus vector database.

REDWOOD CITY, Calif., March 12, 2026 /PRNewswire/ -- Zilliz, the company behind Milvus, the world's most widely adopted open-source vector database, today announced the open-source release of memsearch, a lightweight library that gives AI agents persistent, long-term memory across conversations. Available today under the MIT license, memsearch was engineered by Zilliz's team by extracting and rebuilding the memory subsystem originally developed for OpenClaw—the autonomous AI agent that captured 189,000+ GitHub stars in under two weeks—turning it into a reusable, standalone tool any developer can adopt today.

The AI agent ecosystem has a memory problem. When a conversation ends, most agents forget everything—context, preferences, prior decisions—forcing users to repeat themselves session after session. Existing solutions that attempt to address this typically store information in opaque, proprietary formats that only the AI can access, leaving developers unable to inspect, correct, or migrate what their agent has learned.

Memsearch takes a fundamentally different approach. Rather than abstracting memory behind an inaccessible black box, it stores all agent memories as plain-text files—readable, editable, and version-controllable by any developer. Milvus then automatically indexes those files, enabling fast, accurate semantic retrieval at scale.

"Memory is the missing layer in the AI agent stack. Developers deserve to know what their agents remember, fix it when it's wrong, and carry it forward without lock-in. memsearch is our answer to that—transparent, portable, and built on the open-source foundation the community already trusts." — Jiang Chen, Head of Developer Relations, Zilliz

Why Memsearch — Key Benefits for Developers

• Full transparency: Every memory is a human-readable text file. Developers can see exactly what their AI agent knows—no special tools, no proprietary dashboards required.
• Easy correction: Fix a bad memory by editing a file. memsearch detects the change automatically—no retraining, no data pipelines, no manual re-ingestion.
• Team collaboration: Because memory lives in standard files, teams can apply familiar version-control workflows—Git commits, pull request reviews, rollbacks—to what their agent remembers.
• True portability: Switching machines, AI models, or cloud providers requires nothing more than copying files. There is no proprietary export step, no migration script, no vendor permission.
• Plug-and-play integration: memsearch works with any AI agent framework. A single command installs it; no infrastructure changes are required.

Dedicated Plugin for Claude Code

Alongside memsearch, Zilliz is releasing the memsearch ccplugin—a purpose-built persistent memory plugin for Claude Code, Anthropic's AI-powered coding assistant.

AI-assisted coding sessions accumulate significant context over time: architectural decisions, debugging history, project conventions, and team preferences. Today, that context evaporates when a session ends. The memsearch ccplugin automatically captures session summaries and injects relevant prior context at the start of every new session—so Claude Code arrives informed, not amnesiac.

Installation takes a single command.

For full technical detail on the memsearch architecture and the Claude Code plugin, see the Zilliz engineering blog.

Availability

memsearch is free and open source (MIT license) and is available immediately.

• GitHub: github.com/zilliztech/memsearch
• Documentation: zilliztech.github.io/memsearch
• Claude Code Plugin: zilliztech.github.io/memsearch/claude-plugin

About Zilliz

Zilliz is the company behind Milvus, the world's most widely adopted open-source vector database. Zilliz Cloud brings that performance to production with a fully managed, cloud-native platform built for scalable, low-latency vector search and hybrid retrieval. It supports billion-scale workloads with sub-10ms latency, auto-scaling, and optimized indexes for GenAI use cases like semantic search and RAG.

Zilliz is built to make AI not just possible—but practical. With a focus on performance and cost-efficiency, it helps engineering teams move from prototype to production without overprovisioning or complex infrastructure. Over 10,000 organizations worldwide rely on Zilliz to build intelligent applications at scale.

Headquartered in Redwood Shores, California, Zilliz is backed by leading investors, including Aramco's Prosperity 7 Ventures, Temasek's Pavilion Capital, Hillhouse Capital, 5Y Capital, Yunqi Partners, Trustbridge Partners, and others. Learn more at  Zilliz.com.

REDWOOD CITY, Calif., Feb. 28, 2026 /PRNewswire/ -- Zilliz, the company behind Milvus, the world's most widely adopted open-source vector database, today announced the general availability of Zilliz Cloud BYOC (Bring Your Own Cloud) on Microsoft Azure. With this launch, Zilliz Cloud BYOC is now available across AWS, Google Cloud Platform, and Microsoft Azure—making Zilliz the first managed vector database provider to support BYOC on all three major clouds.

Enterprises building AI applications have long faced a trade-off between managed services that require moving sensitive data outside their security perimeter and self-hosted deployments that demand significant engineering resources. Zilliz Cloud BYOC eliminates this compromise by deploying a fully managed vector database directly inside a customer's own cloud account—enabling organizations to move faster on AI initiatives without sacrificing data control or compliance.

"The AI infrastructure landscape is at an inflection point. Enterprises need platforms that respect their security, compliance, and multi-cloud realities," said Charles Xie, Founder and CEO at Zilliz. "With BYOC on every major cloud, we're removing one of the last barriers to enterprise AI adoption. Organizations no longer have to choose between moving fast and staying in control."

Why the Azure Launch Matters

The Azure launch completes a deliberate expansion—from AWS to GCP and now to Microsoft Azure. For the many enterprises standardized on Microsoft's cloud ecosystem, this launch removes the last deployment barrier. Organizations can now run their vector database in the same environment as Azure OpenAI Service and the rest of their Azure AI stack—eliminating cross-cloud data movement, reducing costs, and keeping AI workflows entirely within a single cloud environment.

Azure customers also benefit from full compatibility with their existing enterprise agreements, reserved capacity, and established governance and compliance frameworks. With the official Zilliz Cloud Terraform Provider, teams can automate BYOC deployments and integrate directly into existing infrastructure-as-code workflows—making adoption seamless for organizations already operating at scale on Azure.

What This Means for Enterprises

• Accelerated AI adoption: Deploy production-grade AI search infrastructure in days, not months, without the engineering burden of managing it.
• Data sovereignty and compliance: All data stays within the customer's own cloud account and jurisdiction, simplifying regulatory requirements.
• Multi-cloud freedom: Teams across different cloud providers can standardize on a single vector database platform without re-platforming.
• Cost transparency: Infrastructure costs flow through existing cloud billing, enterprise agreements, and reserved capacity.

Every BYOC deployment includes the full Zilliz Cloud feature set built on Milvus, along with seamless migration from Pinecone, Qdrant, Elasticsearch, PostgreSQL, OpenSearch, Weaviate, or self-hosted Milvus.

Now Available

Zilliz Cloud BYOC is live across AWS, GCP, and Azure. Get started with deployment guides for AWS, GCP, and Azure, or connect with the Zilliz team to discuss your requirements.

About Zilliz

Zilliz is the company behind Milvus, the world's most widely adopted open-source vector database. Zilliz Cloud brings that performance to production with a fully managed, cloud-native platform built for scalable, low-latency vector search and hybrid retrieval. It supports billion-scale workloads with sub-10ms latency, auto-scaling, and optimized indexes for GenAI use cases like semantic search and RAG.

Zilliz is built to make AI not just possible—but practical. With a focus on performance and cost-efficiency, it helps engineering teams move from prototype to production without overprovisioning or complex infrastructure. Over 10,000 organizations worldwide rely on Zilliz to build intelligent applications at scale.

Headquartered in Redwood Shores, California, Zilliz is backed by leading investors, including Aramco's Prosperity 7 Ventures, Temasek's Pavilion Capital, Hillhouse Capital, 5Y Capital, Yunqi Partners, Trustbridge Partners, and others. Learn more at  Zilliz.com.

REDWOOD CITY, Calif., Feb. 13, 2026 /PRNewswire/ -- Zilliz, the company behind the most popular open-source vector database Milvus, recently announced the availability of a new Zilliz Cloud region in AWS eu-west-1 (Ireland), further expanding its global infrastructure. This new region enables customers—from fast-moving startups to global enterprises—to build and scale AI applications while ensuring data locality, regulatory compliance, and improved performance across Western Europe, the UK, and Ireland.

With data residency and GDPR compliance becoming critical requirements for businesses operating in Europe, the new AWS Ireland region provides developers with greater control over where their data lives—without compromising on performance or flexibility. Ireland is one of the most widely adopted AWS regions in the world and serves as the European base for many of the largest global technology companies.

"As AI adoption accelerates across Europe, enterprises need data infrastructure that keeps pace—close to their users, compliant with local regulations, and ready for production scale," said Charles Xie, CEO at Zilliz. "By adding Ireland to our European footprint alongside Frankfurt, we're giving teams more choice in where they run their AI workloads, helping reduce cross-border data transfer costs while simplifying compliance. It's another step in making Zilliz Cloud the most accessible vector database platform in the world."

Global Infrastructure with Local Performance

Zilliz Cloud now operates across 30 cloud regions globally, making it one of the most geographically distributed vector database platforms available. The Ireland region joins key international deployments across AWS, Google Cloud, and Microsoft Azure in North America, Europe, and Asia-Pacific. Key international regions include:

• AWS: US East (N. Virginia), US East (Ohio), US West (Oregon), Canada (Central), Germany (Frankfurt), Ireland (new!), Singapore, Japan (Tokyo), Australia (Sydney)
• Google Cloud: US West (Oregon), US East (N. Virginia), US Central (Iowa), Germany (Frankfurt), Singapore
• Azure: US East (Virginia), US East 2 (Virginia), US Central (Iowa), Germany West Central (Frankfurt), Central India (Pune), North Europe (Ireland)

This expansion makes it simple for organizations to optimize for performance, data residency, and cost—all while scaling to support the most demanding AI workloads. With auto-scaling, usage-based pricing, and deployment flexibility across providers, Zilliz Cloud helps teams reduce operational overhead and focus on building AI applications that deliver value.

Now Available to All

The AWS Ireland region is now live and available to all Zilliz Cloud customers. Organizations can immediately begin deploying clusters in the new region through the Zilliz Cloud console. New users can create a free account to get started. Teams migrating from other vector databases or regions can take advantage of the Zilliz migration service for a seamless transition.

For more information about this new region, check out the launch blog or connect with our team for help.

About Zilliz

Zilliz is the company behind Milvus, the world's most widely adopted open-source vector database. Zilliz Cloud brings that performance to production with a fully managed, cloud-native platform built for scalable, low-latency vector search and hybrid retrieval. It supports billion-scale workloads with sub-10ms latency, auto-scaling, and optimized indexes for GenAI use cases like semantic search and RAG.

Zilliz is built to make AI not just possible—but practical. With a focus on performance and cost-efficiency, it helps engineering teams move from prototype to production without overprovisioning or complex infrastructure. Over 10,000 organizations worldwide rely on Zilliz to build intelligent applications at scale.

Headquartered in Redwood Shores, California, Zilliz is backed by leading investors, including Aramco's Prosperity 7 Ventures, Temasek's Pavilion Capital, Hillhouse Capital, 5Y Capital, Yunqi Partners, Trustbridge Partners, and others. Learn more at  Zilliz.com.

REDWOOD CITY, Calif., Jan. 31, 2026 /PRNewswire/ -- Zilliz, the company behind the leading open-source vector database Milvus, today announced the open-source release of its Bilingual Semantic Highlighting Model, an industry-first AI model designed to dramatically reduce token usage and improve answer quality in production RAG-powered AI applications.

This highlighting model introduces sentence-level relevance filtering, enabling AI developers to remove low-signal context before sending prompts to large language models. This approach directly addresses rising inference costs and accuracy issues caused by oversized context windows in enterprise RAG and RAG-powered AI deployments.

"As RAG systems move into production, teams are running into very real cost and quality limits," said James Luan, VP of Engineering at Zilliz. "This model gives developers a practical way to reduce prompt size and improve answer accuracy without reworking their existing pipelines."

Key Innovations and Technical Breakthroughs

• Bilingual relevance by design: Optimized for both English and Chinese, the model addresses cross-lingual relevance challenges common in global RAG deployments. It is built on the MiniCPM-2B architecture, enabling low-latency, production-ready performance.
  
  
• Sentence-level context filtering: Rather than scoring entire document chunks, the model evaluates relevance at the sentence level and retains only content that directly supports a user query before sending it to the LLM.
  
  
• Lower token usage, higher answer quality: Zilliz reports that sentence-level filtering significantly compresses prompt size while improving downstream response quality, helping teams reduce inference costs and improve generation speed in production environments.

Availability

The Bilingual Semantic Highlighting Model is available today as an open-source release. To learn more about the training methodology and performance benchmarks, visit the Zilliz Technical Blog.

Download: : zilliz/semantic-highlight-bilingual-v1

About Zilliz

Zilliz is the company behind Milvus, the world's most widely adopted open-source vector database. Zilliz Cloud brings that performance to production with a fully managed, cloud-native platform built for scalable, low-latency vector search and hybrid retrieval. It supports billion-scale workloads with sub-10ms latency, auto-scaling, and optimized indexes for GenAI use cases like semantic search and RAG.

Zilliz is built to make AI not just possible—but practical. With a focus on performance and cost-efficiency, it helps engineering teams move from prototype to production without overprovisioning or complex infrastructure. Over 10,000 organizations worldwide rely on Zilliz to build intelligent applications at scale.

Headquartered in Redwood Shores, California, Zilliz is backed by leading investors, including Aramco's Prosperity 7 Ventures, Temasek's Pavilion Capital, Hillhouse Capital, 5Y Capital, Yunqi Partners, Trustbridge Partners, and others. Learn more at  Zilliz.com.

As Gartner Predicts Vector Databases Will Be Used in 30% of Enterprise Applications by 2026, Milvus Reaches Major Milestone with 10,000+ Production Deployments

REDWOOD CITY, Calif., Dec. 19, 2025 /PRNewswire/ -- Zilliz recently announced that Milvus, its open-source vector database, has surpassed 40,000 GitHub stars, marking one of the fastest growth spurts in the project's history. The milestone comes as vector databases rapidly move into production, with more than 10,000 enterprise teams using Milvus in live AI systems—including NVIDIA, Salesforce, eBay, Airbnb, and DoorDash.

"We're grateful to everyone who supports Milvus—whether they're running it in production, contributing code, reporting issues, or simply following the project," said James Luan, VP of Engineering at Zilliz. "Teams depend on Milvus in demanding environments where performance, reliability, and cost all matter. As adoption grows, we'll keep listening closely to the community and turning that trust into a platform that scales for enterprise production."

2025 Milvus Releases Strengthen Enterprise Adoption

In 2025, Milvus delivered key architectural upgrades that directly improved performance, cost efficiency, and scalability for enterprise production workloads.

Milvus 2.5 introduced native hybrid search, unifying lexical and semantic retrieval in a single engine. This eliminated the operational overhead of maintaining separate search infrastructure, enabling teams to run keyword queries, vector searches, and metadata filters together.

Milvus 2.6 further advanced performance and cost efficiency at scale, with enhancements including:

• Tiered storage reducing costs by up to 50%
• RaBitQ 1-bit quantization cutting memory usage by 72%
• BM25 full-text engine delivering 4× faster performance than Elasticsearch
• Path Index enabling 100× faster JSON filtering
• Support for 100,000+ collections per cluster for multi-tenant deployments

Organizations running Milvus in production report sub-50ms retrieval latency across billions of vectors, while lowering infrastructure costs and improving operational efficiency.

Enterprise-Grade Managed Milvus Service: Zilliz Cloud

The rapid adoption of Milvus has also driven the growth of Zilliz Cloud, the fully managed Milvus service designed for enterprise production environments. Zilliz Cloud includes Cardinal, an advanced vector engine that delivers up to 4× higher performance than open-source Milvus while maintaining 96%+ recall with no manual tuning.

Zilliz Cloud is available across 29 global regions on major cloud providers, including AWS, Azure, and Google Cloud, and offers a 99.95% uptime SLA, SOC 2 Type II compliance, and pay-as-you-go pricing. Customers can reduce the overall total cost of ownership (TCO) by up to 50% compared to self-managed deployments.

Looking Ahead: Milvus Lake

Zilliz is developing Milvus Lake, a semantic-driven multimodal lakehouse for AI-scale data. Built on a manifest + data + index architecture, Milvus Lake will provide trillion-scale storage with predictable latency and integration with Iceberg, Hudi, Spark, and Ray for unified batch processing, semantic retrieval, and training-data preparation.

"Reaching 40,000 stars represents trust from a global developer community building production AI systems," said Charles Xie, Founder and CEO of Zilliz. "As enterprises deploy AI at scale, they need infrastructure that delivers both performance and cost efficiency. Milvus provides that foundation."

About Zilliz

Zilliz is the company behind Milvus, the world's most widely adopted open-source vector database. Zilliz Cloud brings that performance to production with a fully managed, cloud-native platform built for scalable, low-latency vector search and hybrid retrieval. It supports billion-scale workloads with sub-10ms latency, auto-scaling, and optimized indexes for GenAI use cases like semantic search and RAG.

Zilliz is built to make AI not just possible—but practical. With a focus on performance and cost-efficiency, it helps engineering teams move from prototype to production without overprovisioning or complex infrastructure. Over 10,000 organizations worldwide rely on Zilliz to build intelligent applications at scale.

Headquartered in Redwood Shores, California, Zilliz is backed by leading investors including Aramco's Prosperity 7 Ventures, Temasek's Pavilion Capital, Hillhouse Capital, 5Y Capital, Yunqi Partners, Trustbridge Partners, and others. Learn more at Zilliz.com.

Vector Database Leader Recognized for Expertise in Building Production-Ready AI Agents with Amazon Bedrock and AWS Services

REDWOOD CITY, Calif., Dec. 2, 2025 /PRNewswire/ -- Zilliz, creator of the open-source vector database Milvus and the leading provider of cloud-native vector database solutions, announced today that it has achieved the Amazon Web Services (AWS) Agentic AI Specialization, a new category launched within the AWS AI Competency. This specialization recognizes Zilliz as an AWS Partner that enables customers to deploy smart, self-operating AI systems that can think, plan, and work independently to execute complex business processes.

The AWS AI Specialization in Agentic AI distinguishes Zilliz as an AWS Partner with proven technical expertise and customer success in delivering production-ready autonomous AI systems that reason, plan, collaborate, utilize tools, execute tasks, and continuously improve. Zilliz demonstrates expertise in implementing Amazon Bedrock Agents and other leading AWS-compatible frameworks, enabling customers to move beyond AI experimentation to deploy autonomous systems that deliver tangible returns on investment.

"Agentic AI represents the next chapter of enterprise automation," said Charles Xie, CEO and Co-Founder of Zilliz. "Achieving this AWS specialization reflects our shared commitment to giving enterprises the foundation needed to build AI agents that deliver real operational impact—not just prototypes. By combining Zilliz's high-performance vector database with Amazon Bedrock Agents, customers gain the memory, context, and reliability required to move from experimentation to trustworthy autonomous systems at scale."

Zilliz's vector database technology plays a central role in enterprise agentic AI architectures by delivering long-term, high-performance memory for AI agents. Milvus and Zilliz Cloud (managed service of Milvus) provide vector similarity search, multimodal data retrieval, contextual understanding, and persistent state management that autonomous agents need to operate effectively. These capabilities power advanced semantic and multimodal search, Retrieval-Augmented Generation (RAG) pipelines, multi-step reasoning, and multi-agent orchestration across large and sensitive enterprise knowledge bases.

With built-in multitenancy, encryption, role-based access controls, and fine-grained data isolation, Zilliz ensures that AI agents can operate securely across different business units and customer environments while meeting strict compliance requirements. These capabilities are critical for enterprises deploying agentic AI systems that must handle sensitive information, integrate with operational systems, and execute tasks with enterprise-grade reliability and performance.

"Working with Zilliz Cloud has been transformative for our AI agent architecture," said Sasidhar Janaki, Senior Software Engineer at Rexera. "The hybrid search capability alone delivered a 40% improvement in accuracy, and the scalability means we never worry about performance, even during peak traffic periods. It's been essential to our continued growth."

The AWS Agentic AI Specialization ensures customers can confidently select AWS Partners who demonstrate validated expertise in building and implementing enterprise-grade AI agents. These specialized partners, including Zilliz, help organizations deploy autonomous AI systems that can handle end-to-end business processes across diverse use cases, including enterprise knowledge operations, intelligent process automation, autonomous customer operations, financial operations automation, and supply chain optimization.

This expansion of the AWS AI Competency program reflects the growing enterprise demand for AI systems that can operate independently while maintaining human oversight and control. AWS Partners achieving this specialization demonstrate advanced capabilities in delivering both enterprise-ready generative AI and autonomous agentic AI systems to customers across industries.

About Zilliz

Zilliz is the company behind Milvus, the world's most widely adopted open-source vector database. Zilliz Cloud brings that performance to production with a fully managed, cloud-native platform built for scalable, low-latency vector search and hybrid retrieval. It supports billion-scale workloads with sub-10ms latency, auto-scaling, and optimized indexes for GenAI use cases like semantic search and RAG.

Zilliz is built to make AI not just possible—but practical. With a focus on performance and cost-efficiency, it helps engineering teams move from prototype to production without overprovisioning or complex infrastructure. Over 10,000 organizations worldwide rely on Zilliz to build intelligent applications at scale.

Headquartered in Redwood Shores, California, Zilliz is backed by leading investors including Aramco's Prosperity7 Ventures, Temasek's Pavilion Capital, Hillhouse Capital, 5Y Capital, Yunqi Partners, Trustbridge Partners, and others. Learn more at zilliz.com.

Hardware-Accelerated Architecture Brings Enterprise RAG to New Scale and Efficiency

REDWOOD CITY, Calif., Nov. 19, 2025 /PRNewswire/ -- Zilliz, the company behind Milvus, the world's most advanced open-source vector database, today announced a strategic collaboration with Pliops to revolutionize large-scale Retrieval-Augmented Generation (RAG) deployments. By integrating Pliops' LightningAI architecture with Milvus, enterprises can now achieve multi-billion-scale vector search at storage-level costs, breaking through traditional memory constraints that have limited GenAI applications.

As enterprises scale their AI initiatives, vector databases must handle billions of embeddings while maintaining performance and managing costs. This collaboration addresses these challenges head-on by combining Milvus's industry-leading vector search capabilities with Pliops' hardware-accelerated storage technology, enabling efficient large-scale context retrieval and inference for enterprise AI workloads.

Advancing Milvus for Next-Generation AI Infrastructure

Milvus powers mission-critical AI applications across various industries, including semantic search and recommendation systems, as well as agentic AI and RAG. Its distributed, cloud-native architecture is designed for massive scale, and this collaboration takes that capability even further.

Through this partnership, Zilliz will introduce several key enhancements to Milvus in collaboration with Pliops:

• Storage APIs and Tiering: Support for multi-tier storage to optimize cost and performance.
• KV Mapping: Adding a key-value abstraction layer on top of file offsets for efficient caching and retrieval.
• Dual-Tier Architecture:
  • Flash Tier (Hot): Ultra-low latency and high-density access.
  • S3 Tier (Cold): Reliable, globally distributed backup for cost efficiency.

These enhancements allow enterprises to significantly expand context windows, improve inference efficiency, and reduce infrastructure overhead—while maintaining the performance and reliability that Milvus users expect in production environments.

"This collaboration represents a significant leap forward in making enterprise-scale vector search economically viable," said Charles Xie, Founder and CEO of Zilliz. "Pliops' LightningAI introduces a breakthrough approach to scaling GenAI inference, and integrating it with Milvus unlocks truly massive context retrieval at a fraction of the traditional cost. As the creators of Milvus, we're committed to advancing what's possible in vector search. This collaboration gives enterprises a clear path to run larger models, access more knowledge, and deliver faster AI experiences—all without the memory limitations that have constrained GenAI until now."

Ido Bukspan, CEO of Pliops, added, "LightningAI is designed to make AI inference scalable and affordable. Partnering with Zilliz brings the best of storage and retrieval intelligence together."

Availability and Resources

The technical architecture and implementation details, including the Milvus RFC for Near Compute Storage, are available to the open-source community on GitHub. Organizations interested in deploying billion-scale vector search can learn more at:

• Zilliz: https://zilliz.com
• Milvus: https://milvus.io
• Pliops LightningAI: https://pliops.com

About Zilliz

Zilliz develops next-generation vector database technologies that help organizations extract value from unstructured data and accelerate AI application development. The company delivers a fully managed, multi-cloud service, Zilliz Cloud, powered by the open-source Milvus project, with deployments across major cloud platforms in more than 20 countries. Headquartered in Redwood Shores, California, Zilliz is backed by leading investors, including Aramco's Prosperity7 Ventures, Temasek's Pavilion Capital, Hillhouse Capital, 5Y Capital, Yunqi Partners, and Trustbridge Partners. For more information, visit zilliz.com.

Industry-first approach to vector database security enables Fortune 500 companies to deploy AI at scale while meeting the most rigorous compliance requirements.

REDWOOD CITY, Calif. , Aug. 12, 2025 /PRNewswire/ -- Zilliz, the company behind the most popular open-source vector database Milvus, today announced a major expansion of its enterprise security and compliance capabilities, empowering organizations in even the most regulated industries to deploy AI solutions with confidence, speed, and scale.

Security and compliance concerns are the primary obstacles keeping 70% of enterprises from scaling AI beyond pilot programs. Zilliz's enhanced safeguards directly eliminate these barriers, enabling customers to advance from pilot to production in weeks rather than months while maintaining full regulatory compliance.

"Security and compliance are not features we add at the end — they are part of our foundation," said Charles Xie, CEO of Zilliz. "We've built a platform that allows enterprises to unlock the value of unstructured data with the peace of mind that their AI applications are protected by world-class security and certified compliance from the ground up."

Meeting the Rising Bar for AI Trustworthiness

Enterprise AI adoption now hinges on trust. Zilliz treats security as a strategic capability — embedding security-by-design, privacy across jurisdictions, and resilience at scale into the core of its platform so regulated organizations can innovate without hesitation.

The comprehensive framework combines global certifications with enterprise controls built for mission-critical workloads:

• Certified Trust — SOC 2 Type II and ISO/IEC 27001:2022 certifications with continuous third-party validation ensure adherence to the highest standards for security, availability, and confidentiality.
• Global Privacy Compliance — Full GDPR compliance for EU/EEA operations, HIPAA readiness for U.S. healthcare workloads, and official EU-U.S. Data Privacy Framework certification, including UK Extension and Swiss-U.S. DPF.
• Enterprise-Grade Safeguards — AES-256 encryption at rest and TLS 1.2+ in transit; private networking options; role-based access controls (RBAC); and detailed audit logging for full operational transparency
• Guaranteed Uptime — Enterprise SLAs delivering 99.95% availability with financial penalties for non-compliance, backed by automated backup, recovery, and disaster recovery across multiple regions.
• Complete Data Sovereignty — Bring Your Own Cloud (BYOC) deployment keeps sensitive data within customer security perimeters while delivering fully managed vector database performance.

From Open Source Innovation to Enterprise-Ready AI Infrastructure

Zilliz's commitment to secure, compliant AI builds on its heritage as the creator of Milvus, the world's most popular open-source vector database. The same performance and scalability that have made Milvus a global standard are now paired with enterprise protections designed to meet the demands of regulated industries.

"The future of AI will be defined not only by what is possible, but by what is responsible," added Xie. "Our customers can innovate at the speed of AI, knowing their infrastructure meets or exceeds the world's most rigorous security and compliance benchmarks."

For more information about Zilliz's trust framework and security capabilities, visit https://zilliz.com/trust-center.

About Zilliz

Zilliz builds next-generation database technologies that help organizations unlock the value of unstructured data and rapidly develop AI applications. Zilliz offers a fully managed, multi-cloud vector database service powered by open-source Milvus, supporting AWS, GCP, and Azure across 20+ countries.

Headquartered in Redwood City, California, Zilliz is backed by leading investors, including Aramco's Prosperity7 Ventures and Temasek's Pavilion Capital.

This Open-source solution eliminates the multi-billion-dollar gap between benchmark promises and production reality.

REDWOOD CITY, Calif. , July 31, 2025 /PRNewswire/ -- Zilliz, the company behind the popular open-source vector database Milvus, recently announced the release of VDBBench 1.0, an open-source benchmarking platform designed to test vector databases under realistic production conditions. Unlike traditional benchmarks that rely on static data and idealized scenarios, VDBBench evaluates systems during streaming data ingestion, metadata filtering, and concurrent workloads that mirror actual enterprise deployments.

"The vector database market has experienced explosive growth since 2023, but our benchmarking methodologies haven't kept pace," said James Luan, VP of Engineering at Zilliz. "Organizations are making multi-million dollar infrastructure decisions based on misleading benchmarks that don't reflect production realities. VDBBench 1.0 fundamentally changes this dynamic by establishing new standards for authentic, production-relevant performance evaluation."

• Advanced Filtering Analysis: Systematically tests metadata filtering across selectivity levels (50% to 99.9%), revealing the "hidden performance killer" that dramatically impacts query speeds and recall accuracy in production.
• Streaming Read/Write Testing: Simulates continuous data ingestion while serving queries, conditions where many databases fail despite impressive static benchmarks.
• Modern Datasets: Uses vectors from state-of-the-art embedding models, including OpenAI and Cohere, with dimensions ranging from 768 to 1,536, reflecting current AI workloads.
• Custom Dataset Support: Organizations can benchmark using their production data and embedding models for industry-specific testing requirements.
• Production-Focused Metrics: Prioritizes P95/P99 tail latency, sustainable throughput under load, and recall accuracy for realistic capacity planning.

VDBBench also features a redesigned dashboard with interactive visualizations that help engineers quickly identify performance gaps. Testing results for major platforms including Milvus, Zilliz Cloud, Pinecone, and Elasticsearch are available on the VDBBench Leaderboard.

VDBBench is available on GitHub with complete documentation and community support. Organizations ready to move beyond misleading benchmarks can access the platform immediately and customize it for specific testing requirements.

Download VDBBench 1.0 → | View Leaderboard → | Contact us for Support

Zilliz builds next-generation database technologies that help organizations unlock the value of unstructured data and rapidly develop AI applications. Headquartered in Redwood Shores, California, Zilliz is backed by leading investors, including Aramco's Prosperity7 Ventures and Temasek's Pavilion Capital. Learn more at www.zilliz.com.

REDWOOD CITY, Calif., July 17, 2025 /PRNewswire/ -- Zilliz, creator of the open-source vector database Milvus, today announced the availability of Zilliz Cloud in the new AI Agents and Tools category of AWS Marketplace. Customers can now use AWS Marketplace to easily discover, purchase, and deploy AI agents solutions, including Zilliz Cloud using their existing AWS accounts, accelerating the development of AI agents and agentic workflows.

With Zilliz Cloud, developers can rapidly build and deploy retrieval-augmented generation (RAG) pipelines, semantic search systems, and multimodal AI applications—without the burden of managing infrastructure at scale.

"We're excited to offer Zilliz Cloud in AWS Marketplace," said Charles Xie, Founder and CEO of Zilliz. "This makes it easier for customers to operationalize intelligent agents with high-performance vector search, built-in scalability, and enterprise-grade reliability—all within the AWS environment they already trust."

Zilliz Cloud delivers critical capabilities, including sub-10ms vector search latency, hybrid search that combines vector similarity with metadata filtering, and support for billion-scale datasets. Built for real-world performance, the platform provides optimal search strategies and zero manual tuning through its AI-powered AutoIndex and Cardinal Search Engine. It is a cloud-native database with a distributed architecture designed for on-demand scalability and cost-efficient growth.

With the availability of AI Agents and Tools in AWS Marketplace, customers can significantly accelerate their procurement process to drive AI innovation, reducing the time needed for vendor evaluations and complex negotiations. With centralized purchasing using AWS accounts, customers maintain visibility and control over licensing, payments, and access through AWS.

To learn more about Zilliz Cloud in AWS Marketplace, visit Zilliz Cloud Vector Database - Built on Milvus (pay-as-you-go). To explore the new AI Agents and Tools category in AWS Marketplace, visit https://aws.amazon.com/marketplace/solutions/ai-agents-and-tools/.

About Zilliz

Zilliz builds next-generation vector database technologies that help organizations unlock the value of unstructured data and accelerate the development of AI and machine learning applications. By simplifying complex data infrastructure, Zilliz brings the power of AI within reach for enterprises, teams, and individual developers alike.

Zilliz offers a fully managed, multi-cloud vector database service powered by the open-source Milvus project. The service supports major cloud platforms, including AWS, and is available in more than 20 countries and regions.

Headquartered in Redwood Shores, California, Zilliz is backed by leading investors including Aramco's Prosperity7 Ventures, Temasek's Pavilion Capital, Hillhouse Capital, 5Y Capital, Yunqi Partners, Trustbridge Partners, and others.

New region empowers customers to meet data sovereignty, regulatory, low-latency, and cost-efficiency goals when building AI applications.

REDWOOD SHORES, Calif., July 14, 2025 /PRNewswire/ -- Zilliz, the company behind the most popular open-source vector database Milvus, today announced the availability of a new Zilliz Cloud region in Azure Central India, further expanding its global infrastructure. This new region enables customers—from fast-moving startups to global enterprises—to build and scale AI applications while ensuring data locality, regulatory compliance, low-latency performance, and lower cloud costs.

With data residency becoming a critical requirement for many businesses operating in India and nearby markets, the new Azure Central India region provides developers with greater control over where their data lives, without compromising on performance or budget.

"Developers rely on Zilliz Cloud every day to build and scale AI applications more quickly, efficiently, and cost-effectively," said Charles Xie, CEO at Zilliz. "By adding a new region in India, we're helping customers reduce cross-border data transfer costs and latency, while also simplifying compliance with local regulations. It's a win-win for both innovation and infrastructure spend."

Global Infrastructure with Local Performance

Zilliz Cloud  now operates across 26 cloud regions globally, making it one of the most geographically distributed vector database platforms available. The Central India region joins key international deployments across AWS, Google Cloud Platform (GCP), and Microsoft Azure in North America, Europe, and Asia-Pacific. Key international regions include:

• AWS: US East (N. Virginia), US East (Ohio), US West (Oregon), Canada (Central), Germany (Frankfurt), Singapore, Japan (Tokyo)
• Google Cloud: US West (Oregon), US East (N. Virginia), US Central (Iowa), Germany (Frankfurt), Singapore
• Azure: US East (Virginia), US East 2 (Virginia), US Central (Iowa), Germany West Central (Frankfurt), Central India (new!)

This expansion makes it simple for organizations to optimize for latency, locality, and cost, all while scaling to support billions of vector embeddings and the most demanding GenAI workloads. With auto-scaling, usage-based pricing, and deployment flexibility across providers, Zilliz Cloud helps teams reduce operational overhead and focus on building AI features that deliver value.

Companies like Sarvam, a leading AI startup building multilingual models in India, exemplify the demanding performance requirements driving this expansion. "We needed a system that could handle real-time retrieval over millions of knowledge vectors without breaking under load," said Dr. Pratyush Kumar, Co-Founder of Sarvam. "Zilliz gave us that. It freed up engineering cycles and let us focus on improving reasoning on the model side, not managing infrastructure."

Now Available to All

The Azure Central India region is now live and available to all Zilliz Cloud customers. Organizations can immediately begin deploying clusters in the new region through the Zilliz Cloud console.

For more information about this new region, check out this launch blog or connect with our technical team for help.

About Zilliz

Zilliz builds next-generation database technologies that help organizations unlock the value of unstructured data and rapidly develop AI and machine learning applications. By simplifying complex data infrastructure, Zilliz brings the power of AI within reach for enterprises, teams, and individual developers alike.

Headquartered in Redwood Shores, California, Zilliz is backed by leading investors including Aramco's Prosperity7 Ventures, Temasek's Pavilion Capital, Hillhouse Capital, 5Y Capital, Yunqi Partners, Trustbridge Partners, and others.

Learn more at www.zilliz.com or explore the open-source Milvus project at www.milvus.io.

Vector database technology enables intelligent automation in real estate, financial services, and beyond

SAN FRANCISCO, July 11, 2025 /PRNewswire/ -- Zilliz, the company behind the open-source Milvus vector database, today announced that leading enterprises are deploying AI agents at scale using Zilliz Cloud as their foundational infrastructure. Companies like Verbaflo.ai and Rexera are transforming business operations through intelligent agents that deliver human-like responsiveness.

The AI agent market is experiencing explosive growth as businesses automate complex workflows while maintaining personalized customer experiences. Zilliz Cloud has emerged as critical infrastructure enabling this transformation, powering conversational AI agents that understand context, retrieve information instantly, and engage in natural dialogue.

AI Agents Reshaping Business Operations

Verbaflo.ai revolutionized real estate with AI agents handling customer inquiries, property management, and communications 24/7 across voice, chat, and email channels. "Zilliz Cloud has become a strategic enabler for our vision of transforming conversational AI across industries," said Rachit Jindal, Senior AI Engineer at Verbaflo.ai.

Leading AI company Rexera operationalized AI agents at scale for complex closing processes, powered by Zilliz Cloud infrastructure. Their agents process over 10,000 tasks daily and millions of pages monthly, serving 350+ real estate firms.

The Infrastructure Behind Intelligent Automation

As enterprises move beyond simple chatbots to sophisticated AI agents, Zilliz Cloud provides the vector database foundation, enabling agents to understand context and maintain conversation continuity. The platform supercharges AI agent performance at scale, delivering the speed and reliability needed for enterprise deployments.

Organizations looking to deploy intelligent AI agents can learn more about Zilliz Cloud at zilliz.com/cloud or contact us for deployment consultations.

About Zilliz

Zilliz is a US-based global leader building next-generation vector database technologies, helping organizations unlock the value of unstructured data and rapidly develop AI applications. Zilliz offers a fully managed, multi-cloud vector database service powered by open-source Milvus, supporting AWS, GCP, and Azure across 20+ countries.

Headquartered in Redwood Shores, California, Zilliz is backed by leading investors including Aramco's Prosperity7 Ventures, Temasek's Pavilion Capital, Hillhouse Capital, and others.

Media Contact 

Chris Churilo, VP of Marketing
PR@zilliz.com

Dual recognition from G2 validates Zilliz's breakthrough approach to delivering enterprise-grade performance without operational complexity.

SAN FRANCISCO, July 11, 2025 /PRNewswire/ -- Zilliz, the company behind the world's most popular open-source vector database Milvus, today announced it has been recognized as both "Highest Performer" and "Easiest to Use" in G2's Summer 2025 Grid^® Report for Vector Databases. The dual recognition positions Zilliz as the only vector database vendor to achieve top rankings in both performance and usability categories simultaneously.

Rare Achievement Reflects Customer-Driven Market Leadership

G2's Grid^® Reports, considered the industry gold standard for enterprise software evaluation, are based exclusively on authenticated reviews from over 60 million verified software buyers. The ranking methodology evaluates vendors across Market Satisfaction and Market Presence, with results determined solely by customer feedback and real-world deployment experiences.

"This dual recognition is unprecedented in our industry and validates our fundamental belief that enterprises should never have to choose between performance and simplicity," said  Charles Xie, CEO and Co-founder of Zilliz. "Our customers are telling us loud and clear that we've solved the traditional trade-off that has plagued database technology for decades."

Industry-Leading Performance Meets Operational Simplicity

The "Highest Performer" designation reflects Zilliz Cloud's superior technical capabilities, delivering up to 50,000 queries per second with sub-millisecond latency while scaling to billions of vectors. This performance advantage is powered by Zilliz's proprietary Cardinal search engine and AI-driven AUTOINDEX technology, which eliminates the manual tuning traditionally required for high-performance database deployments.

Simultaneously, the "Easiest to Use" recognition highlights Zilliz's fully managed service approach, which abstracts infrastructure complexity without compromising enterprise-grade capabilities. Customer testimonials consistently highlight reductions in deployment timelines from months to weeks, with one enterprise customer noting that they can now "focus entirely on product innovation rather than database management."

Broad Market Adoption from Startups to Fortune 500

Zilliz's customer base of over 10,000 organizations demonstrates the platform's versatility across various company sizes and industries. Fortune 500 enterprises, including Walmart, Salesforce, NVIDIA, IBM, and Bosch, rely on Zilliz for mission-critical workloads, from e-commerce recommendation engines to autonomous vehicle data processing, which delivers measurable business impact.

Equally important is Zilliz's success with AI-native startups and mid-market companies such as Read.AI, which serves millions of users with lightning-fast retrieval, and emerging innovators like beatoven.ai. This broad adoption across the full spectrum of company sizes validates Zilliz's ability to scale with organizations as they grow, eliminating the need for costly platform migrations as businesses evolve from proof-of-concept to enterprise-scale deployments.

Open Source Foundation Drives Market Differentiation

Built on Milvus, the world's most adopted open-source vector database with over 35,000 GitHub stars and 100 million downloads, Zilliz Cloud offers enterprises unique evaluation flexibility and technology transparency. This open-source foundation addresses vendor lock-in concerns while enabling customers to test core functionality before committing to managed services.

The G2 recognition comes as the vector database market experiences explosive growth, with search interest increasing 11 times since January 2023, as AI applications transition from experimental to production-critical infrastructure.

About Zilliz

Zilliz is a US-based global leader building next-generation vector database technologies, helping organizations unlock the value of unstructured data and rapidly develop AI applications. Zilliz offers a fully managed, multi-cloud vector database service powered by open-source Milvus, supporting AWS, GCP, and Azure across 20+ countries.

Headquartered in Redwood Shores, California, Zilliz is backed by leading investors including Aramco's Prosperity7 Ventures, Temasek's Pavilion Capital, Hillhouse Capital, and others.

Media Contact 

Chris Churilo, VP of Marketing
PR@zilliz.com 

Global initiative recognizes passionate individuals building the future of AI-powered vector search through open-source vector database technology

SAN FRANCISCO, June 18, 2025 /PRNewswire/ -- Zilliz, the company behind the leading open-source vector database Milvus, today announced the launch of the Milvus Ambassador Program, a global initiative designed to recognize and support passionate individuals who believe in the power of AI infrastructure and vector databases. The program creates opportunities for developers, advocates, and anyone who loves to share knowledge, inspire innovation, and make friends to contribute to the rapidly growing AI developer community.

The Milvus Ambassador Program addresses the increasing demand for vector database expertise as organizations worldwide implement AI-powered vector search and retrieval systems. By fostering a global network of contributors, the program aims to accelerate the adoption of Milvus technology while empowering developers to become thought leaders in AI infrastructure innovation.

"The future of AI-powered applications depends on robust infrastructure, and vector databases are at the heart of that infrastructure," said Chris Churilo, VP of Marketing at Zilliz. "Our ambassador program recognizes that the most impactful innovations come from passionate community members who share knowledge, mentor others, and push the boundaries of what's possible with vector database technology."

What Ambassadors Can Expect:

• Visibility and recognition through Milvus's digital channels and media
• Exclusive Milvus swag and badges
• Skill-building opportunities in community leadership and developer advocacy
• Opportunities to speak at local events, meetups, and conferences to grow regional communities (travel covered)
• Join a global network of contributors dedicated to the success of Milvus
• Direct collaboration with Milvus engineering teams and core contributors, providing feedback and influence on product direction

Who Should Apply?

The program is open to developers, researchers, content creators, and technical leaders with experience using Milvus vector databases and a passion for empowering others through content, events, and code. Ambassadors can contribute at their own pace, with flexible engagement levels.

Visit the Milvus Community Page to learn more about the program, or apply now by filling out the application form.

About Zilliz

Zilliz is a US-based global leader building next-generation vector database technologies, helping organizations unlock the value of unstructured data and rapidly develop AI and machine learning applications. By simplifying complex data infrastructure, Zilliz brings the power of AI within reach for enterprises, teams, and individual developers alike. Zilliz offers a fully managed, multi-cloud vector database service powered by open-source Milvus, supporting major cloud platforms such as AWS , GCP, and Azure, and is available across more than 20 countries and regions.

Headquartered in Redwood Shores, California, United States, Zilliz is backed by leading investors including Aramco's Prosperity7 Ventures, Temasek's Pavilion Capital, Hillhouse Capital, 5Y Capital, Yunqi Partners, Trustbridge Partners, and others.

REDWOOD SHORES, Calif., June 15, 2025 /PRNewswire/ --  Zilliz, creator of the world's most widely adopted open-source vector database, Milvus, today announced significant adoption of its vector database solutions by video surveillance providers addressing critical industry challenges. As the global video surveillance market, valued at over $62 billion and growing rapidly, evolves from passive monitoring tools to intelligent, proactive security solutions, organizations using Zilliz Cloud and Milvus report breakthrough capabilities in overcoming data overload, eliminating manual monitoring inefficiencies, and achieving real-time threat detection.

Traditional video surveillance systems struggle with data overload from underutilized footage, time-consuming manual monitoring processes, and data silos that prevent cross-domain intelligence integration. Surveillance platforms implementing Zilliz Cloud vector databases are solving these persistent challenges by transforming vast amounts of video data into actionable intelligence through vector embeddings that represent visual context and meaning.

"The video surveillance industry is undergoing a massive transformation from reactive monitoring to proactive intelligence," said Charles Xie, CEO of Zilliz. "Traditional surveillance systems create bottlenecks with manual processes prone to human error and data overload that limits effectiveness. Our customers are building AI-native security solutions that can process vast amounts of visual data in real-time, detect anomalies instantly, and provide actionable insights that were previously impossible to achieve."

Major Surveillance Platforms Report Breakthrough Performance

Leading cloud-based surveillance providers report transformative results after transitioning from traditional databases to Zilliz Cloud's vector search technology. A major multi-tenant surveillance platform serving businesses from retailers with thousands of locations to small enterprises managing just a few sites achieved significant improvements in video retrieval performance. The platform now delivers sub-second search capabilities across months of footage using natural language queries such as "person in red jacket near loading dock" or "vehicle parked longer than 30 minutes."

"Vector databases have solved the fundamental challenge of extracting meaningful insights from massive video datasets," said a technology executive at the surveillance provider. "We can now provide our customers with instant, accurate search results that would have taken hours of manual review with traditional systems."

Organizations implementing these AI-powered capabilities report security teams can now detect threats and respond up to 50% faster than traditional monitoring methods, while automated anomaly detection significantly reduces false positives and operational costs by eliminating extensive manual monitoring requirements.

Enterprise customers across retail operations, industrial safety, transportation infrastructure, and smart city initiatives are deploying these capabilities to achieve advanced loss prevention, automated safety monitoring, passenger flow analysis, and privacy-compliant public safety tracking.

Zilliz Cloud Delivers Enterprise-Scale Performance

Zilliz Cloud's distributed architecture addresses enterprise-scale video processing demands through several key capabilities. The platform processes billions of video vectors with sub-100ms latency while auto-scaling to accommodate traffic spikes and varying workloads. Built-in security, encryption, and compliance features protect sensitive video data, while multi-tenant support enables surveillance providers to serve diverse customer bases efficiently.

The vector database approach converts video footage into high-dimensional mathematical representations, enabling sophisticated AI analysis and semantic understanding that supports both real-time monitoring and forensic investigation. This technology eliminates traditional surveillance limitations by breaking down data silos and integrating video insights with other operational systems.

Industry Adoption Accelerates with Responsible AI Focus

As AI becomes more embedded in surveillance systems, Zilliz emphasizes responsible development practices aligned with privacy regulations such as GDPR. This US-based company's solutions maintain transparency and security standards while designing AI enhancement to augment human capabilities rather than replace security professionals, enabling teams to focus on complex decision-making while automation handles routine monitoring tasks.

The integration of AI and vector databases positions surveillance systems for continued evolution, including edge computing implementations, AI-powered video summarization, and autonomous surveillance capabilities that will further improve security operations while reducing operational costs.

Solutions Available for Enterprise Implementation

Organizations implementing AI-powered video surveillance can learn more about Zilliz Cloud at zilliz.com/cloud or contact sales for deployment consultations.

About Zilliz

Zilliz is a US-based global leader building next-generation vector database technologies, helping organizations unlock the value of unstructured data and rapidly develop AI and machine learning applications. By simplifying complex data infrastructure, Zilliz brings the power of AI within reach for enterprises, teams, and individual developers alike. Zilliz offers a fully managed, multi-cloud vector database service powered by open-source Milvus, supporting major cloud platforms such as AWS, GCP, and Azure, and is available across more than 20 countries and regions.

Headquartered in Redwood Shores, California, United States, Zilliz is backed by leading investors including Aramco's Prosperity7 Ventures, Temasek's Pavilion Capital, Hillhouse Capital, 5Y Capital, Yunqi Partners, Trustbridge Partners, and others.

"I've long been passionate about democratizing AI by making the underlying technologies more accessible and affordable for everyone," said Charles Xie, CEO at Zilliz. "For over a year, I've emphasized that cost reduction is critical for widespread AI adoption. As data volumes continue to grow exponentially, organizations require vector database solutions that can scale efficiently while maintaining cost control. Milvus 2.6 furthers our commitment to this vision with innovations that streamline infrastructure requirements and optimize resource utilization—all while maintaining the high performance our users expect."

Continuing Our Mission: Cost Reduction Across Multiple Dimensions

Monetary Savings: Lower Infrastructure & Storage Bills

Milvus 2.6 introduces several innovations that directly reduce infrastructure costs:

• Tiered Storage with Hot/Cold Data Separation: Automatically moves frequently accessed vectors to high-performance storage while relegating less-used data to more economical options—reducing storage costs without compromising retrieval performance. Works seamlessly with leading storage providers including Cohesity, Pure Storage, MinIO, and NetApp.
  
  
• Int8 Vector Compression for HNSW Indexes: Stores dense vectors using 8-bit integers, substantially reducing memory requirements while maintaining search accuracy.
  
  
• RabitQ 1-bit Quantization: Pushes quantization to an extreme to achieve comparable retrieval quality with only half memory cost.
  
  
• New Write-Ahead Log (WAL) with Woodpecker: Eliminates the need for external message queues like Kafka or Pulsar, featuring a diskless architecture that reduces infrastructure costs while improving write performance.

Organizations migrating from OpenSearch to Milvus have reported up to 8x cost reductions while maintaining or improving performance for vector search workloads.

Operational Efficiencies: Less Infrastructure to Manage

Milvus 2.6 simplifies operations with its innovative diskless architecture:

• Streaming Node: A new dedicated component for real-time data ingestion built directly into the platform—eliminating the need for the costly external message queues on the write path.
  
  
• CDC + BulkInsert: Combines Change Data Capture (CDC) with bulk data ingestion feature, simplifying data replication across instances in different geolocation.
  
  
• Storage v2 Format: Optimized for performance and future compatibility with data processing frameworks like Apache Spark.
  
  
• APT/YUM Deployment: Native package support simplifies installation and upgrades, reducing operational overhead.

Developer Time: More Built-In Tools, Less Plumbing

Milvus 2.6 boosts developer productivity with:

• Data-In, Data-Out: Enables direct ingestion of raw content (text, images, audio) with built-in inference capabilities—eliminating separate pre-processing pipelines.
  
  
• Custom Reranker: Allows developers to apply custom scoring logic using scalar fields and user-defined functions.
  
  
• Text & JSON Search: Native support for advanced text processing capabilities including:
  • Advanced tokenization for Asian languages (Japanese/Korean)
  • JSON path/flat/key indexing
  • Match & phrase queries
    
    
• Sampling + Aggregation Queries: Built-in analytics tools for fast iteration during development.

Open Source & Trusted by Developers

Milvus is fully open source with permissive licensing (Apache 2.0) and developer-friendly architecture. With no black boxes, organizations can contribute, audit, and customize as needed—ensuring transparency and flexibility.

Already a Leader in Vector Search

Milvus has established itself as one of the most widely adopted vector databases in the world, powering AI applications at scale for more than 10,000 organizations worldwide across a wide range of use cases.

"The integration between Milvus 2.6 and MinIO creates a powerful solution for AI workloads requiring both performance and cost efficiency," said Anand Babu Periasamy, CEO and co-founder of MinIO. "By enabling data to be written directly to MinIO instead of using Kafka and supporting hot/cold tiered storage strategies, Milvus 2.6 users can achieve significant infrastructure simplification while maintaining performance for their vector search applications."

For more information on Milvus 2.6 and its groundbreaking features, visit the Milvus website and read our blog post.

About Zilliz

Zilliz is an American SaaS company that builds next-generation vector database technologies, helping organizations unlock the value of unstructured data and rapidly develop AI and machine learning applications. By simplifying complex data infrastructure, Zilliz brings the power of AI within reach for enterprises, teams, and individual developers alike. Zilliz offers a fully managed, multi-cloud vector database service powered by open-source Milvus, supporting major cloud platforms such as AWS, GCP, and Azure, and is available across more than 20 countries and regions.

Headquartered in Redwood Shores, California, Zilliz is backed by leading investors including Aramco's Prosperity7 Ventures, Temasek's Pavilion Capital, Hillhouse Capital, 5Y Capital, Yunqi Partners, Trustbridge Partners, and others.

REDWOOD CITY, Calif., June 3, 2025 /PRNewswire/ -- Zilliz, creator of the world's most widely adopted open-source vector database, Milvus, introduced a powerful new set of Migration Services designed to make moving unstructured data and vector embeddings between platforms fast, reliable, and cost-free. These solutions eliminate the technical and operational barriers that typically slow down AI data infrastructure modernization.

"Organizations working with unstructured data for AI applications face migration challenges that traditional ETL pipelines simply can't solve," said James Luan, VP of Engineering at Zilliz. "Our new tools provide the missing infrastructure layer — making it easy to migrate from Elasticsearch to Milvus, consolidate across multiple vector stores, or move to Zilliz Cloud with zero disruption."

Breaking Down Migration Barriers for Unstructured Data

Unstructured data — including images, text, audio, and video — now accounts for over 90% of enterprise data. As organizations turn this data into vector embeddings, they run into major roadblocks:

• Format Variety: Unstructured data exists in diverse formats (JSON, CSV, Parquet, images, etc.), requiring specialized processing
• System Fragmentation: Business information is scattered across S3, HDFS, Kafka, data warehouses, and data lakes
• Vendor Lock-in Risks: Moving vector embeddings between databases often creates technical dependencies and potential vendor lock-in
• Complex Transformations: Converting unstructured data requires AI model integration for embedding generation and schema mapping

Two Flexible Options for Every Environment

Zilliz offers Migration Services that directly respond to these challenges through two complementary deployment options:

• Zilliz Migration Service provides a free, fully managed solution with zero configuration requirements and zero downtime. This service handles all aspects of migration while maintaining continuous synchronization between source and target systems.
• Vector Transport Service (VTS), available as open-source software, offers the same capabilities for organizations that require self-hosted deployments in secure or air-gapped environments.

Purpose-Built for AI and Vector Workloads

Both solutions deliver essential features specifically designed for unstructured data and vector embeddings:

• Zero-Downtime Migrations: Continuous synchronization keeps applications running seamlessly during transitions
• Broad Source Compatibility: Support for Elasticsearch, Pinecone, Qdrant, PostgreSQL, Milvus, and more
• Flexible Migration Modes: Options for one-time batch imports or real-time streaming synchronization
• Purpose-Built for Unstructured Data and Vector Embeddings: Specialized handling with schema mapping and transformations
• Enterprise-Grade Reliability: Designed for massive datasets with robust monitoring and alerting

Empowering Data Freedom Across Industries

Organizations across sectors are already using Zilliz Migration Services to transform their AI infrastructure:

• A global retailer migrated 200 million product embeddings from Elasticsearch to Zilliz Cloud, improving search accuracy by 40% while cutting infrastructure costs in half
• A healthcare organization moved patient data vectors between systems while maintaining strict HIPAA compliance
• A financial services provider eliminated vendor dependency by moving to an open-source foundation while maintaining continuous operation

"Migrating between platforms without rebuilding pipelines from scratch is a game-changer for our AI strategy," said one customer. "What would have taken months of engineering was completed in days, allowing us to focus on innovation rather than infrastructure management."

Availability

Zilliz's new migration solutions are now generally available:

• Zilliz Migration Service: Available as a free, fully managed service within Zilliz Cloud
• Vector Transport Service: Available as open-source software under the Apache 2.0 license atgithub.com/zilliztech/vts

For more information about Zilliz Migration Services, visit zilliz.com/zilliz-migration-service or contact support.

About Zilliz

Zilliz is an American SaaS company that builds next-generation vector database technologies, helping organizations unlock the value of unstructured data and rapidly develop AI and machine learning applications. By simplifying complex data infrastructure, Zilliz brings the power of AI within reach for enterprises, teams, and individual developers alike. Zilliz offers a fully managed, multi-cloud vector database service powered by open-source Milvus, supporting major cloud platforms such as AWS, GCP, and Azure, and is available across more than 20 countries and regions.

Headquartered in Redwood Shores, California, Zilliz is backed by leading investors including Aramco's Prosperity7 Ventures, Temasek's Pavilion Capital, Hillhouse Capital, 5Y Capital, Yunqi Partners, Trustbridge Partners, and others.