The ecosystem at a glance
| Component | Role |
|---|---|
| Studio | Agent builder — design, configure, and manage agents. Agent health dashboards are powered by Prometheus, which collects metrics from Runtime, Studio, and InsightHub via the shared OTel pipeline. |
| Runtime | Event-driven execution platform for agents. Orchestrates inference, multi-agent runs, context-aware prompting, memory strategies, tool execution, and channel connectors. Built for Kubernetes and OpenShift deployments. |
| InsightHub | AI-powered knowledge exploration — create Topics, upload documents, and explore them through streaming AI conversation powered by the Runtime. |
| Twyd | Knowledge base service. Handles document ingestion, topic management, and vector search. Used by InsightHub and the Runtime for RAG retrieval. |
The agent lifecycle
When you build an agent in Studio, here’s what happens end-to-end:- You configure an agent in Studio (model, system prompt, tools, memory, etc.)
- Studio saves the configuration to the Runtime Registry — the central store for all agent configs
- When a user sends a message, the Runtime fetches the agent config from the Registry
- The Runtime executes the agent: constructs the prompt, calls the LLM, runs tools if needed, applies memory
- Telemetry from the run — along with telemetry from Studio and InsightHub — flows through the shared OpenTelemetry pipeline; Prometheus collects the metrics and feeds Studio’s dashboards, where you review agent health and usage
Next steps
Ecosystem overview
See every service, its port, and what it does.
Installation
Get the stack running locally with Docker Compose.