Reference
CRDs, the kmctl CLI, metrics, and endpoints.
- Agent CRD
- Crew CRD : The Crew CRD groups Agents into one team and configures crew-wide settings such as the discussion gateway and the shared working memory the agents use.
- Models in Kubemoot : The Kubemoot model layer: the ModelServer, Model, and EmbeddingModel CRDs, how the scheduler binds agents to them, load on demand, the catalog, and GPU fit on the reference hardware.
- RAGSource Guide : RAGSource manages a retrieval knowledge source end to end: cloning documents, chunking, embedding through a model server, storing in pgvector, and verifying the index.
- KubemootConfig Guide : KubemootConfig is the cluster-scoped singleton that holds default images and settings for every Kubemoot component, keeping versions out of the operator source.
- MCPServer Guide : The MCPServer CRD deploys Model Context Protocol servers on Kubernetes, injects the mcp-bridge sidecar for stdio, sets probes, and registers with gateways.
- MCPGateway Guide : MCPGateway deploys the hub that routes agent tool calls to MCPServers. Agents connect to the gateway, which discovers and manages the matching servers.
- CrewFitnessSuite CRD : Run fitness scripts against a crew many times with a CrewFitnessSuite and collect every iteration into an XLSX report stored in the NATS Object Store.
- MootArchetype CRD : The MootArchetype resource: the declared phases, signals, and state machine of a consensus archetype. A v1alpha1 API that the operator validates today and the agent runtime does not yet read.
- ADL Reference : The complete ADL vocabulary: prompt keywords and fitness assertions.
- Skill CRD : The Skill resource: a crew-level procedure written in ADL that the coordinator selects on demand and injects into the agents working a discussion. Every spec and status field, how selection and loading work, and an example.
- kmctl Reference : Command reference for the kmctl command-line tool.
Crew CRD
The Crew CRD groups Agents into one team and configures crew-wide settings such as the discussion gateway and the shared working memory the agents use.
Models in Kubemoot
The Kubemoot model layer: the ModelServer, Model, and EmbeddingModel CRDs, how the scheduler binds agents to them, load on demand, the catalog, and GPU fit on the reference hardware.
RAGSource Guide
RAGSource manages a retrieval knowledge source end to end: cloning documents, chunking, embedding through a model server, storing in pgvector, and verifying the index.
KubemootConfig Guide
KubemootConfig is the cluster-scoped singleton that holds default images and settings for every Kubemoot component, keeping versions out of the operator source.
MCPServer Guide
The MCPServer CRD deploys Model Context Protocol servers on Kubernetes, injects the mcp-bridge sidecar for stdio, sets probes, and registers with gateways.
MCPGateway Guide
MCPGateway deploys the hub that routes agent tool calls to MCPServers. Agents connect to the gateway, which discovers and manages the matching servers.
CrewFitnessSuite CRD
Run fitness scripts against a crew many times with a CrewFitnessSuite and collect every iteration into an XLSX report stored in the NATS Object Store.
MootArchetype CRD
The MootArchetype resource: the declared phases, signals, and state machine of a consensus archetype. A v1alpha1 API that the operator validates today and the agent runtime does not yet read.
ADL Reference
The complete ADL vocabulary: prompt keywords and fitness assertions.
Skill CRD
The Skill resource: a crew-level procedure written in ADL that the coordinator selects on demand and injects into the agents working a discussion. Every spec and status field, how selection and loading work, and an example.
kmctl Reference
Command reference for the kmctl command-line tool.