kagent-dev/kagent
Kubernetes-native framework for building AI agents
- Chart
- Not on a chart right now
- Stars
- 4.4k
What it is
kagent is a Kubernetes-native framework for building, deploying, and managing AI agents. It uses Kubernetes custom resources such as Agent, AgentTemplate, and ModelConfig to declaratively define agent behavior and runtime configuration.
Who it is for
Developers and platform engineers running AI agents on Kubernetes or integrating them with infrastructure and DevOps tools would use it.
Why it is trending
It recently released v1.0.1 and gained 169 stars today. It stands out by managing multiple runtimes—including Go and Python ADKs, Codex, and Claude—alongside OpenTelemetry tracing and session snapshots through Kubernetes APIs.
Main features
- Declarative agent management via Kubernetes custom resources and kubectl
- Support for OpenAI, Azure OpenAI, Anthropic, Google Vertex AI, Ollama, and custom gateways
- Built-in MCP server with tools for Kubernetes, Istio, Helm, Argo, Prometheus, Grafana, and Cilium
- Persistent sessions in PostgreSQL with suspend, resume, fork, and OpenTelemetry tracing
Summarized on November 17, 2026 from the README and repository data. It can be wrong; check the source before relying on it. Report a wrong summary