Solo Kagent Enterprise, bridges agentic K8S-AI infrastructure gap
Cloud-native connectivity company Solo has detailed kagent enterprise, a context-aware platform for AI & agentic applications on Kubernetes.
The company says that this release solves the security, observability, resiliency and governance requirements that prevent AI and agentic projects from moving forward from pilot stages to love production.
According to the ebulliently effervescent Solo CEO Idit Levine, Kubernetes (K8S) provides a strong foundation for cloud-native applications, but it lacks the “contextual awareness required for generative and agentic applications.
What does she think K8S is lacking in this regard?
The ability to secure, scale and govern agents, tools and large language models.
But, she suggests, kagent enterprise fills this gap by extending Kubernetes with “context-aware networking and context-aware runtime components” that natively support agent-native protocols such as MCP and A2A.
This allows platform and AI teams to implement AgentOps for any tool server or agent framework – like Agent Development Kit and Langchain – used in their agentic applications.
“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 Levine. “Kagent enterprise fills these important gaps by effectively and securely transforming cloud native infrastructure into agentic infrastructure.”
As noted, kagent enterprise provides context-aware networking through agentgateway, an agent-native data plane optimised for agentic AI connectivity with support for MCP, A2A and leading LLM provider protocols.
Created by Solo.io and contributed to the Linux Foundation, Levine claims that agentgateway takes a “more comprehensive approach to AI connectivity” than any other AI gateway in the market, supporting LLM consumption, agent-to-agent and agent-to-tool interactions across any tool server or agent framework.
Context-aware runtime
The technology includes context-aware runtime: kagent enterprise introduces a new runtime layer for agents and tools that extends Kubernetes to become context-aware. Unlike traditional cloud native runtimes that treat workloads as a black box, agentic runtimes require a new identity and policy model for agents acting on behalf of users, advanced failover and memory management for agents and deeper observability instrumentation to explain and audit how agents and tools interact.
Kagent enterprise has built-in support for creating and deploying agents and tools, but also integrates with alternative agentic frameworks (e.g. Agent Development Kit, Langchain) and any MCP-compliant tool server implementation. Launched in March 2025 and quickly adopted as a CNCF project, kagent has grown to 800+ community members and 100+ contributors as the community-backed foundation for agentic infrastructure.
Also here, kagent enterprise brings context-aware connectivity and runtime together with a centralised management plane to provide AgentOps – a unified platform for managing and securing agentic infrastructure.
The AgentOps dashboard gives teams centralized visibility with an agent graph and end-to-end tracing of user, agent, tool and LLM interactions. Policy and lifecycle management are built in, with declarative APIs and UI controls to create, deploy, update and retire agents. An agent registry makes it easy to discover available agents and tools, while human-in-the-loop and human-on-the-loop controls provide the safeguards enterprises need to scale agentic applications with confidence.
Overall, kagent enterprise is designed to offer trust and observability built into the cloud-native infrastructure layer so that platform teams can access the agentic AI while ensuring quality and security in production.