Run and Govern AI Agents in Kubernetes
kagent brings identity, policy, and observability to every AI agent running in Kubernetes, with agentregistry to catalog and govern the agents, MCP tools, and skills your teams are already building. Built for real agent orchestration, not just another framework.
Open source and community-driven
The fastest-growing agent runtime in cloud native
Backed by contributions from the world's leading technology companies. kagent is a CNCF Sandbox project, and just getting started.
Months
Community
Contributors
GitHub Stars
Why Teams Choose Us
“Every agent needs a way to prove who it’s acting as, and what it’s allowed to do.”
kagent gives every agent a verifiable identity and granular, policy-governed access, with human-in-the-loop approval for the actions that need a second set of eyes.
“Every team is spinning up agents, MCP tools, and skills with no central inventory or approval process.”
agentregistry gives you one open source, AI-native registry to catalog, discover, and govern every agent and tool your organization runs.
“Orchestrating and scaling agents across clusters and clouds by hand doesn’t hold up as agent orchestration needs grow.”
kagent runs natively in Kubernetes so you can orchestrate, scale, and observe AI agents with the same operational discipline you apply to the rest of your infrastructure.
Trust & compliance
SOC 2
Certification supports security and procurement review for regulated Kubernetes environments
OSS roots
Build on Envoy, Istio, Cilium, and Gateway API foundations for open source service mesh adoption.
CNCF maintainer status
keeps Solo.io engineers close to the projects shaping cloud native mesh standards.
FIPS builds
provide FIPS 140-2 validated options for service mesh security requirements.
Published SLAs
Define support expectations for enterprise service mesh operations.
Customer references
include production outcomes from teams running large-scale Kubernetes networking.
Frequently Asked Questions
What is Solo.io's platform for AI agents?
What is Solo.io's platform for AI agents?
kagent is a Kubernetes-native runtime for building and running AI agents, adding identity, policy, tracing, and lifecycle management to the infrastructure you already run. agentregistry pairs with it as an open source registry to catalog and govern every agent, MCP tool, and Agent Skill your teams deploy.
What agent frameworks does kagent support?
What agent frameworks does kagent support?
kagent is framework-agnostic. It supports LangChain, CrewAI, Google ADK, and A2A agents out of the box, along with any MCP tool or custom agent your team has already built, so you don't have to standardize on one framework to get production-grade orchestration.
How does kagent handle AI agent orchestration in Kubernetes?
How does kagent handle AI agent orchestration in Kubernetes?
kagent is a CNCF Sandbox project for building and running AI agents natively in Kubernetes, giving you the same orchestration, scaling, and observability model your platform team already uses for the rest of your workloads.
What is agentregistry, and do I need one for agentic AI?
What is agentregistry, and do I need one for agentic AI?
agentregistry is an open source, AI-native registry for cataloguing, discovering, and governing AI agents, MCP tools, and Agent Skills. Once more than one team is shipping agentic AI, a registry keeps that sprawl from becoming unmanageable.
Is this open source, or do I need an enterprise contract?
Is this open source, or do I need an enterprise contract?
Most teams running kagent and agentregistry in production choose Solo's enterprise support for the SLAs and production hardening that come with it. The underlying projects are open source, donated to vendor-neutral foundations under the Linux Foundation, so they also remain free to run on your own if you'd rather self-support.
See kagent Run AI Agents in Your Cluster
Request a demo to see how kagent and agentregistry bring identity, policy, and observability to AI agents in your environment, or compare your options in the Buyer's Guide first.
