
Agents, teams, workflows, and connected AgentOS runtimes
Govern the agent lifecycle
Build, test, debug, improve, and operate against local or deployed runtimes.Follow every run
Open a session and follow the execution behind its response. Trace trees show the model calls, tool inputs and outputs, team delegation, and workflow steps recorded for the run. Spans show status and timing. Model spans also include token metrics when available.
Inspect the execution path behind a run
Manage the system behind each run
Studio
Compose components from your Registry, save drafts, publish versions, and choose the version served by the API.
Knowledge and memory
Search knowledge content and review or update the user memories exposed by the connected runtime.
Evaluations and metrics
Review stored evaluation results and aggregate runtime usage from the configured database.
Approvals
Inspect tool arguments, approve or reject paused executions, and follow resolution history.
Scheduler
Create recurring runs, trigger them manually, and inspect their execution history.
Full Control Plane guide
Follow a first run, review runtime requirements, and open deeper guides.
Connect your runtimes
Add local, staging, and production AgentOS endpoints to the Control Plane. Select a runtime from the header to change the system you are working on. The browser sends requests to the selected AgentOS endpoint. That runtime executes components, applies its authorization configuration, and reads or writes the state shown in the UI.Serve production runtimes over HTTPS and configure Security & Auth before connecting them.