A Kubernetes-native framework for building, deploying and managing AI agents as custom resources.
Sources and review #
Checked against public documentation on . Suitability guidance is our editorial judgment; this is not a performance benchmark or an endorsement.
Platform teams that want AI agents operating inside Kubernetes under the same GitOps controls as everything else.
About kagent #
kagent defines agents, their LLM providers and MCP tools as Kubernetes custom resources, so agents are built, deployed and managed like other cluster workloads. It supports OpenAI, Azure OpenAI, Anthropic, Google Vertex AI, Ollama and custom providers through AI gateways, and is aimed at DevOps and platform automation.
kagent is listed in this index written primarily in Go, with 4.0k stars on GitHub. Its latest recorded repository push was in October 2026; that is not an ASE editorial review date.
Make your product part of the discovery. Explore advertising
kagent and related category tools #
| Record | Stars | Pricing | ||
|---|---|---|---|---|
| kagentthis listing | 4.0k | Go | Apache-2.0 | Costs not checked |
| [Browserbase](https://agentsearchengine.app/agents/browserbase) | — | — | — | Freemium |
| [toolhive](https://agentsearchengine.app/agents/toolhive) | 2.3k | Go | Apache-2.0 | Costs not checked |
| [skillhub](https://agentsearchengine.app/agents/skillhub) | 5.2k | Java | Apache-2.0 | Costs not checked |
| [Pipecat Cloud](https://agentsearchengine.app/agents/pipecat-cloud) | — | — | — | Paid product |
| [Arize Phoenix](https://agentsearchengine.app/agents/arize-phoenix) | 12k | Python | Elastic-2.0 | Free |