Solo.io, a leading provider of cloud native connectivity and AI-ready infrastructure, has launched Kagent Enterprise, a context-aware platform designed for AI and agentic applications on Kubernetes. This solution addresses key security, observability, resiliency, and governance challenges that hinder AI projects from progressing beyond pilots to production.
Kubernetes offers a solid base for cloud native applications but falls short in providing the contextual awareness needed for GenAI and agentic applications to handle security, scaling, and governance for agents, tools, and large language models. Kagent Enterprise bridges this gap by enhancing Kubernetes with context-aware networking and runtime components that support agent-native protocols like MCP and A2A. This allows platform and AI teams to implement AgentOps for tool servers or agent frameworks such as Agent Development Kit and Langchain.
“Navigating the path to production with AI agents is hard and requires critical gaps in the Kubernetes foundation to be filled to meet the unique requirements for agents, tools, and LLMs,” said Idit Levine, CEO and Founder of Solo.io. “Kagent enterprise fills these important gaps by effectively and securely transforming cloud native infrastructure into agentic infrastructure.”
Kagent Enterprise includes agentgateway, an agent-native data plane optimized for AI connectivity, with full support for MCP, A2A, and protocols from leading LLM providers. Developed by Solo.io and contributed to the Linux Foundation, agentgateway offers a comprehensive approach to AI connectivity, covering LLM consumption, agent-to-agent, and agent-to-tool interactions across any tool server or agent framework.
The platform introduces a runtime layer that makes Kubernetes context-aware, moving beyond traditional runtimes that view workloads as black boxes. For agentic applications, it incorporates a new identity and policy model for agents acting on users' behalf, advanced failover and memory management, and enhanced observability to audit interactions between agents and tools. Kagent Enterprise supports built-in agent and tool deployment while integrating with frameworks like Agent Development Kit and Langchain, as well as MCP-compliant tool servers. Launched as a CNCF project in March 2025, kagent has grown to over 800 community members and 100 contributors.
Kagent Enterprise combines connectivity and runtime with a centralized management plane for AgentOps, offering unified visibility through an agent graph and end-to-end tracing of interactions involving users, agents, tools, and LLMs. It includes policy and lifecycle management with declarative APIs and UI controls for creating, deploying, updating, and retiring agents. An agent registry simplifies discovery of available agents and tools, while human-in-the-loop controls ensure secure scaling.
“As cloud native organizations embrace agentic AI, the real opportunity lies in moving beyond pilots to enterprise-wide impact. Kubernetes alone was not designed to handle the scale, complexity, and security demands of AI workloads,” said Paul Nicholson, Research VP, Cloud and Datacenter Networking at IDC. “IDC research shows enterprises will be deploying large numbers of AI enabled applications within the next year, it is essential these applications have a foundation for security, observability, and scalability, to make AI agents truly enterprise-ready and unlocking an entirely new generation of AI-driven use cases on Kubernetes.”
With Kagent Enterprise, platform teams gain greater trust and observability in cloud native infrastructure, facilitating easier access to agentic AI while maintaining production quality and security.
Solo.io is reimagining infrastructure for cloud and AI, uniting secure, seamless cloud connectivity with AI-ready, agentic infrastructure. Trusted by leading enterprises worldwide, Solo.io helps organizations securely connect applications, services, and AI workloads across any environment. From AI infrastructure to API gateways and service mesh, our solutions simplify and unify application networking, enabling teams to accelerate innovation, scale intelligently, and leverage the full potential of modern AI agents.