A Kubernetes-native framework for building, deploying, and managing AI agents.
kagent is worth checking the docs before setup with trust notes worth reviewing. Check agent compatibility and use-case fit before adding it to your workflow.
gh repo view kagent-dev/kagent --webOpen the official repository or website.
Check the README for package manager, auth, and platform requirements.
Try it in a small test task inside your agent workflow.
Repository setup guidance
Looks usable, but maintenance, license, or security notes deserve a closer look.
Last commit was about 24 days ago.
3528 GitHub stars indicate community interest.
138 open issues signal maintenance load.
Apache-2.0 license detected.
3 security/trust notes recorded.
Setup difficulty is 4/5.
Official NVIDIA-verified skills for AI agents to use CUDA-X libraries and platform tools correctly.
Official Elastic Agent Skills library for AI coding agents to work with Elasticsearch, Kibana, Observability, and Security.
Local GitHub Actions runner for AI agents — test CI/CD workflows locally before pushing.
Open-source LLM app development platform. Build AI workflows, RAG pipelines, and agents with a visual interface.
kagent lets you build AI agents that run on Kubernetes, the popular system for managing software containers. It uses Kubernetes custom resources to define agents, their tools, and the AI models they use. This makes it easy to manage AI agents like other cloud applications.
kagent is a Kubernetes-native framework designed to simplify the lifecycle of AI agents. It leverages Kubernetes custom resources to define agents, their tools, and LLM configurations, enabling declarative management and scalability. The framework supports multiple LLM providers including OpenAI, Azure OpenAI, Anthropic, Google Vertex AI, and Ollama, as well as custom providers via AI gateways. Agents can connect to any MCP server for tools, and kagent includes a built-in MCP server with tools for Kubernetes, Istio, and Helm. It is part of the CNCF ecosystem and follows open-source best practices. The project provides a UI for managing agents and is designed to be easy to understand and use, offering a flexible and powerful way to build and manage AI agents in cloud-native environments.
3,528
Stars
707
Forks
138
Issues
Apache-2.0
License
A Kubernetes-native framework for building, deploying, and managing AI agents.
Kubernetes developers, DevOps engineers, AI/ML engineers
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
Requires Kubernetes expertise; misconfiguration could expose agents or data. LLM API keys and sensitive data must be securely managed in Kubernetes secrets.
Similar or complementary options to evaluate include NVIDIA Agent Skills, Elastic Agent Skills, Agent-CI.
Aug 20, 2026