Appearance
AgentOps
AgentOps in prokube covers the operational path for building, connecting, exposing, and observing AI agents on controlled workspace infrastructure.
Use Labs for interactive development and debugging. Use AgentOps when an agent should run as a managed workspace workload rather than inside an interactive session.
Main Workflows
| Workflow | Use |
|---|---|
| Agents | Create kagent agents, attach model configurations and tools, test conversations, and expose agents over A2A. |
| LLM Serving | Deploy self-hosted OpenAI-compatible models for agents and other LLM clients, including tool-calling support where available. |
| MCP Servers | Run governed MCP tool servers in a workspace and expose their tools to agents, OpenCode, and external MCP clients. |
| Memory Stores | Provide workspace-scoped state and retrieval capabilities for agent workflows. |
| Agent Gateway | Expose models, MCP servers, agents, and serving endpoints to external clients through scoped API keys. |
Typical Flow
- Choose a model path: use an administrator-granted external model, create a workspace Model Configuration, or deploy an in-cluster model with LLM Serving.
- Prepare any tools the agent needs: deploy MCP Servers or connect another agent.
- Create an Agent, attach the Model Configuration, select the MCP or agent tools it may call, and test it in the built-in chat.
- Expose programmatic access through Agent Gateway only when external clients, SDKs, CI jobs, or other integrations need to call the service without a browser session.
- Use logs, events, metrics, traces, and API-key usage data to debug behavior and review operational impact.
Access Model
AgentOps separates browser-based UI work, internal workspace traffic, and external API traffic.
| Access path | Typical caller | Authentication |
|---|---|---|
| UI | A user working in pkui | Browser session and workspace permissions |
| Internal workspace traffic | Agents, MCP servers, models, and other workloads in the same workspace | Kubernetes and mesh identity |
| External API traffic | SDKs, automation, CI jobs, external MCP clients, and A2A callers | Agent Gateway API key scoped to the target service |
You usually need API keys only for external clients. In-workspace agents and tools normally use the platform's internal identity and routing model.
Foundation
AgentOps workloads run on the shared prokube Foundation. Start with these cross-cutting pages when you need platform behavior rather than feature-specific usage: