Yugabyte Launches Meko, a Data Infrastructure to Solve the Multi-Agent Memory and Knowledge Problem

New platform supports compounding memory, shared knowledge, and full decision traceability to enable continuous learning for agentic applications

SUNNYVALE, Calif.--(BUSINESS WIRE)--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.

Meko introduces a new storage paradigm that gives AI developers a shared layer for memory, knowledge, conversation history, and observability, replacing the brittle stack of relational databases, vector stores, document stores, caches, and object storage, which IT teams are forced to stitch together.

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.

Meko is built on YugabyteDB, a horizontally scalable, PostgreSQL-compatible distributed database that natively supports SQL, NoSQL, vector, time-series, and graph queries. This means a single query can span multiple data models without stitching, unlocking higher performance and lower costs.

Meko enables agents to share learnings with other agents and humans alike. Context management is complex and requires tremendous engineering effort, even more than application development. Meko simplifies it by unifying data constructs required for modern multi-agentic applications. In addition, it supports collective memory, which aggregates information across the system rather than relying on localized agent memory. Continuously adding to the shared knowledge from conversations, providing real-time data access, and maintaining current knowledge bases with the required explainability and traceability are critical for modern enterprise knowledge management.

"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."

As an agent-native data infrastructure, Meko enhances the AI data layer and provides three key values to enterprises:

• Shared Knowledge and Compounding Memory: 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.
• Built for the Economics of Agentic Workloads: 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.
• Auditability for an Era of AI Regulation: 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.

Enabling the Next Generation of AI Applications

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.”

Flexible Deployment and Open Source

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.

Developers can get started by requesting access at www.mekodata.ai or find out more by joining the YugabyteDB community on Discord at mekodata.ai/discord.

About Yugabyte

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. Learn more information at www.yugabyte.com.