kagent
Cloud Native Agentic AI | Discord: https://bit.ly/kagentdiscord
What is kagent?
Cloud Native Agentic AI | Discord: https://bit.ly/kagentdiscord
Overview of kagent
What it is
kagent is a Kubernetes native framework for building AI agents. It is designed to make it easy to build, deploy, and manage AI agents within Kubernetes, the most popular orchestration platform for running workloads. The framework is built around Kubernetes custom resources and aims to be understandable and flexible.
Key features
- Agents: The main building block, a Kubernetes custom resource that combines behavior and runtime configuration.
- Agent Templates: Share system prompts, tools, subagents, and LLM configuration across agents.
- Harnesses: Define how an agent runs, supporting Go and Python ADKs, Codex, Claude, and custom runtimes.
- LLM Providers: Support for OpenAI, Azure OpenAI, Anthropic, Google Vertex AI, Ollama, and custom providers via ModelConfig resources.
- MCP Tools: Connect to MCP servers for tools covering Kubernetes, Istio, Helm, Argo, Prometheus, Grafana, Cilium, and others.
- Sessions: Persist conversation and task history, with suspend/resume and checkpoint/fork capabilities.
- Observability: OpenTelemetry tracing for monitoring agent and tool execution.
Use cases
- Building and deploying AI agents that interact with Kubernetes clusters and cloud-native ecosystems.
- Managing agent lifecycles declaratively through YAML and GitOps workflows.
- Connecting agents to external tools via MCP servers for operations like monitoring, networking, and deployment.
- Creating testable, observable agents with session persistence and tracing.
Getting started
See the repository README for installation instructions and guidance on creating your first agent.
License and pricing
This project is licensed under the Apache 2.0 License. It is open source and free to use.
Based on the project's public README and repository metadata.