Kkagent logo

kagent Unclaimed

Developer Platforms

kagent.dev

Kagent is an open-source CNCF sandbox project by Solo.io for building and running AI-driven agents on Kubernetes.

kagent is an open-source, CNCF sandbox project originated by Solo.io. It provides a cloud-native framework for building, deploying, and operating AI-driven agents within Kubernetes. The project includes a Kubernetes controller that manages agent lifecycles, an engine that runs the agent runtime, a dashboard and CLI for management, and a suite of MCP tooling to support Model Context Protocol servers and agent-enabled workflows. kagent supports running agents and MCP tools in Kubernetes, emphasizes safe, observable operations, and offers documentation to install, start, and extend its capabilities. The target audience includes developers building agent-based automation, site reliability engineers, and organizations seeking scalable, secure orchestration of autonomous capabilities in production. Its core concepts cover architecture components, runtimes, observability, and provider integrations.

To empower developers and operations teams to create, deploy, and manage autonomous agents within Kubernetes, enabling scalable, secure, and observable agent-based automation through MCP servers, tooling, and clear guidance.

What we offer

kagent

Build and orchestrate AI agents in Kubernetes with efficient resource management and full observability.

kagent.dev/

kmcp

Accelerate MCP service development and deployment with kmcp's streamlined workflows.

github.com/kagent-dev/kmcp

Market segments

Market size by segment

Growth potential (CAGR)

Autonomous Agent Orchestration

6.27 Billion USD35.32% CAGR

Capabilities to compose, coordinate, and monitor multi-agent workflows, including memory and context management for autonomous AI agents.

Model Context Protocol deployment

0.9 Billion USD35% CAGR

Tooling and deployment workflows for Model Context Protocol (MCP) services, including project scaffolding, container image packaging, CRD-based service management, support for stdio/HTTP transports, and agentgateway integration for secure tool communications.

AI governance and agent monitoring

0.43 Billion USD34.3% CAGR

Monitors autonomous AI agents and models for policy compliance, performance, and risk; provides enforcement, audit capabilities, and analytics to govern AI-driven actions.

Federated and scalable runtime management

0.1 Billion USD27.3% CAGR

Management of federated, multi-cluster Kubernetes deployments for AI runtimes, enabling multi-cluster federation, centralized control of agent fleets, production-grade Postgres-backed storage, and operational scalability.

More information about our offering

kagent

Kubernetes-native agent runtime for running AI agents inside Kubernetes. kagent defines agents as Kubernetes CRDs, provides a production-grade runtime, observability, and governance for agent workloads. It supports multiple runtimes (Go and Python ADK), brings your own frameworks, NVIDIA NemoClaw guardrails, and a suite of MCP tooling to integrate with MCP servers. The platform emphasizes declarative operations, GitOps-driven deployment, and full observability via OpenTelemetry and Prometheus. It targets developers building agent-based automation, site reliability engineers, and organizations seeking scalable, secure orchestration of autonomous capabilities in production.

  • Ensures Fast Startups
    Agents benefit from rapid initialization through snapshot restoration rather than cold booting, leading to improved responsiveness.
  • Ensures Transparency
    Provides comprehensive monitoring features that allow users to analyze and understand agent behavior and performance.
  • Delivers Context-Aware Distribution
    This feature enables enterprises to run and manage AI agents efficiently, ensuring they can handle production demands securely and effectively.
  • Ensures Reliable Operations
    With comprehensive production support, businesses can trust that their kagent configurations are backed by expert guidance, reducing downtime and improving performance.
  • Facilitates Collaboration
    Enable agents to interact seamlessly, enhancing functionalities by allowing coordinated tasks and workflows.
  • Streamlines Management
    Facilitates DevOps workflows with familiar tools, making it straightforward to manage agent lifecycles.
  • Enhances Security
    Ensures safe agent operations with robust security measures to govern interactions and deployments.
  • Streamlines Agent Management
    This feature empowers users with tools that enhance visibility and control over their deployed agents, allowing for more efficient troubleshooting and maintenance.
  • Facilitates Scalable Operations
    This support allows enterprises to run and manage agents consistently across diverse environments, adding flexibility and efficiency to agent deployments.
  • Supports Diverse Frameworks
    Flexibility to integrate various agent frameworks allows users to leverage existing tools and technologies.
  • Enhances Development Choices
    Developers can select the optimal language for their use case, fostering rapid innovation and adaptability.
  • Provides Reliable Storage
    Utilizes familiar technologies for data storage to facilitate ease of access, management, and integration.
  • Facilitates Hands-On Learning
    Access to training labs allows users to become proficient in kagent and MCP tools, ensuring effective implementation and utilization within their environments.
  • Reduces Token Usage
    Enhances memory usage by summarizing conversations, preventing excessive token consumption while maintaining conversation quality.
  • Improves User Experience
    Allows agents to retain context across sessions, enhancing continuity and user interactions.
  • Promotes Efficiency
    Encourages the use of standardized prompts across agents, streamlining interaction design and development.

kmcp

KMCP is a lightweight toolkit to take MCP servers from prototype to production. It provides end-to-end workflow support to scaffold, containerize, and deploy MCP services in Kubernetes, using CRDs and standard tooling. It also offers built-in integration with agentgateway for secure tool communications and supports multiple transports, all designed to simplify production-grade MCP development.

  • Secure Agent Communications
    Integrate with agentgateway to ensure secure communication between agents and tools while maintaining observability and governance.
  • Streamlined Deployment Process
    Leverage kmcp deploy to easily rollout your MCP services in Kubernetes, customizing transport and configuration options.
  • Simplify Image Management
    Effortlessly create and manage container images for your MCP services, enabling simpler deployments across environments.
  • Kubernetes Native Management
    Utilize Custom Resource Definitions to manage the lifecycle of your MCP services within the Kubernetes ecosystem.
  • Accelerated Project Setup
    Quickly initialize new MCP projects using best practice templates, streamlining your development process.
  • Flexible Transport Options
    Switch between different transport methods based on your architecture needs, allowing greater flexibility in service integration.

References

Methodology and sourcing behind the figures shown above.

Autonomous Agent Orchestration

Primary estimate uses Mordor Intelligence’s Agentic AI Orchestration and Memory Systems report, which specifically targets orchestration plus memory layers and reports a 2025 market size of USD 6.27B and a 2025–2030 CAGR of 35.32%. Comparable industry reports for adjacent definitions (AI agents / multi-agent orchestration) show 2025 market sizes spanning roughly USD 4.2B–12.8B and CAGRs from ~18% to ~46%, indicating consensus around a multi‑billion dollar market with high (mid‑to‑high double-digit) growth potential.

Model Context Protocol deployment

Estimated segment size uses published MCP ecosystem projections and measured adoption signals from the provided results. Gupta's market projection ($1.2B → $4.5B) was used as a total‑ecosystem anchor; MCPCrawler and Anthropic/registry statistics (server counts, SDK downloads, and enterprise production adoption) indicate strong developer and enterprise uptake. Assuming deployment/tooling (project scaffolding, packaging, CRDs, transports, agent‑gateway integration) represents roughly 15–20% of the broader MCP ecosystem yields ~0.9B. High recent adoption and registry growth imply rapid continued adoption; conservatively estimate a 35% CAGR for deployment tooling over the near term.

AI governance and agent monitoring

Multiple market reports in the provided results place the AI governance market (which includes agent monitoring) in the low hundreds of millions USD in the mid-2020s, with strong multi‑year growth forecasts. Reported mid‑2020s market values range ~USD 0.31–0.62B; CAGR forecasts vary from ~28% to 51% depending on scope. I selected ~USD 0.43B as a midpoint estimate for current market size and a CAGR of ~34.3% reflecting the central tendency of specialist governance forecasts (Mordor, Precedence, Persistence) while acknowledging higher agent/agentic‑AI growth projections for adjacent agent markets.

Federated and scalable runtime management

Estimate anchored to a focused ‘‘federated learning platforms’’ market dataset that directly covers orchestration, agent fleets, and coordinator services (components matching federated, multi-cluster runtime management). Marketgenics values the federated learning platforms market at USD 0.1B in 2025 and projects a 27.3% CAGR to 2035; broader federated-learning reports (PrecedenceResearch, IMARC) show larger but variable totals for the overall federated learning market, supporting a view of rapid growth and sizeable upside for platform and runtime orchestration subsegments. Chosen figures use Marketgenics as the primary, closely aligned source and the other reports to indicate addressable-market context and variance in published estimates.

Related Organizations