.jpg)
Yugabyte, the distributed AI database experts, today announced the launch of Meko, an agent-native data infrastructure designed specifically for multi-agent AI systems that work and learn together. As enterprises increasingly deploy AI agents to automate complex workflows, Meko solves a fundamental and growing challenge: how to give agents the persistent, shared memory and knowledge they need to compound their learning over time.
Yugabyte launches Meko, agent-native data infrastructure for multi-agent AI systems with shared memory and knowledge.
Meko introduces Datapack, a portable multi-tenant data store that persists per-agent memory while making knowledge shareable across entire agent system.
Built on YugabyteDB, a horizontally scalable, PostgreSQL-compatible distributed database supporting SQL, NoSQL, vector, time-series, and graph queries.
Serverless, multi-tenant design keeps costs low when agents are idle and scales seamlessly when active.
Provides complete traceable audit trail of what agents learn, how they share knowledge, and data operations for EU AI Act compliance.
Available as fully managed service; open-source version planned with community-driven development model.
AI agents generate and consume dynamic data, including conversation histories, contextual knowledge, operational traces, and long-term memory. Orchestration across these data sources and proper context transfer are required to enable effective agent interactions. Meko addresses this challenge and related context sprawl by unifying the associated systems into a single, purpose-built data infrastructure for agentic applications.
Built from the ground up to support AI data needs such as knowledge, memory, conversations, and traces, Meko exposes agent-native actions, such as “add knowledge”, that directly represent the AI data constructs used by AI agents. Developers can now build and interact with these abstracted functions through standard interfaces (MCP) while Meko automatically manages how data is stored, indexed, and optimized across underlying storage systems.
"There is no data infrastructure today that seamlessly allows combined learning and sharing across agents and humans," said Karthik Ranganathan, co-founder and CEO of Yugabyte. "Meko solves this through collective memory, a shared foundation where every agent's learning compounds across the entire system, not just within a single context window."
Meko introduces the concept of a Datapack. This portable, multi-tenant data store persists per-agent memory while making knowledge shareable across an entire system of agents. This means that when one agent learns something, it appends the new information to its knowledge, and all users benefit. Critically, Meko also preserves the reasoning context and decision traces behind that knowledge. So, when Agent B picks up where Agent A left off, it inherits not just the output, but also the understanding that shaped it.
Meko is architected from the ground up for the bursty, variable nature of agentic applications. Its serverless, multi-tenant design means costs stay low when agents are idle and scale seamlessly when they're active. Storing entire chat transcripts and then passing them to the next agent is neither ideal nor cost-effective. The right context has to be extracted and managed. Meko automatically extracts context and tiers older data from high-performance SSDs to object stores like S3, and warms it back up on demand. This gives developers an enterprise-grade storage layer without enterprise-grade complexity or cost.
Regulators worldwide are moving toward mandatory documentation requirements for high-risk AI systems, including under the EU AI Act. Meko provides a complete, traceable audit trail of what agents learn, how they share that knowledge, and what data operations underpin every interaction. All memory reads and writes route through a single MCP endpoint backed by a unified database, making compliance a feature of the architecture rather than an afterthought.
AI agents are becoming crucial to enterprise workflows, from powering customer support automation to serving as internal copilots and operating complex autonomous systems. The need for a reliable and scalable data layer is now critical. By delivering an agent-native architecture that manages knowledge, memory, and conversations, Meko provides developers with the foundational infrastructure they need to build the next generation of intelligent applications.
"Meko is about removing the friction between ideas and production," added Ranganathan. "When developers no longer have to worry about how to manage agent state, they can move faster and build more powerful AI experiences."
Meko is currently available as a fully managed service, allowing organizations to get started quickly without managing infrastructure. The platform will support multi-region and multi-cloud deployments, enabling global scale and high availability for production AI systems. Staying true to YugabyteDB's open-source heritage, the company plans to make Meko available as open-source software and follow a community-driven development model. Developers can run Meko locally for experimentation or deploy it across private clouds, public clouds, or hybrid environments.
Yugabyte is the company behind YugabyteDB, the open-source, high-performance distributed SQL database for building global, AI, and cloud-native applications. Designed for the data demands of the AI-era, YugabyteDB serves business-critical applications with SQL query flexibility, high performance, and cloud-native agility, allowing enterprises to focus on business growth instead of complex data infrastructure management. It is trusted by companies in cybersecurity, financial markets, IoT, retail, e-commerce, and other verticals. Founded in 2016 by former Facebook and Oracle engineers, Yugabyte is backed by Lightspeed Venture Partners, 8VC, Dell Technologies Capital, Sapphire Ventures, and others.
TechIntelPro empowers B2B technology decision-makers with the latest industry trends, deep insights, leadership perspectives and actionable intelligence to drive both organizational and professional milestones—and thrive on the tech pulse.