Getting started
Install Krypton, verify the UI and gateway, and choose your next guide.
Documentation
Start here for Krypton concepts, tutorials, operations, and reference.
Krypton is a Kubernetes-native runtime for AI agents, self-hosted LLMs, and MCP servers.
For agents, Krypton turns A2A, plain HTTP, and framework-backed containers into cluster resources with stable gateway routing, lifecycle management, scaling signals, and observability.
For model serving, Krypton turns a Model custom resource into a
llama.cpp deployment, pulls GGUF weights from Hugging Face, and exposes
the result through OpenAI-compatible API paths (/v1/models,
/v1/chat/completions, /v1/completions, /v1/embeddings). Your
applications can use familiar SDKs while operators manage models as
ordinary Kubernetes resources.
For MCP, Krypton runs HTTP-transport servers directly or bridges stdio servers into the same agent gateway and UI introspection path.
Start by intent
| If you want to… | Go here |
|---|---|
| Install Krypton and confirm the gateway and UI are healthy | Getting started |
| Deploy a real workload step by step | Tutorials |
| Understand the resource model and request path | Concepts |
| Configure ingress, metrics, and production troubleshooting | Operations |
| Look up exact fields, flags, and chart values | Reference |
Fast path
- Install Krypton.
- Deploy your first Agent or deploy your first LLM.
- Read the architecture when you are ready to tune routing, scaling, or operations.
Tutorials
Guided paths for deploying agents, MCP servers, and self-hosted LLMs.
Concepts
The mental model for Krypton’s resources, routing, and runtime components.
Operations
Production-facing setup for ingress, observability, and troubleshooting.
Reference
API, CLI, and Helm chart references.
Roadmap
What’s planned next.