Works with the agentsyou already run.
Where your agent runs decides what Sulcus can do with it. Find yours, then follow its setup.
Hosted by Sulcus
Sulcus runs your Python agent from a public Git repository. Watch it live, stop it and set a token limit.
Graph and node steps, model and tool calls, tokens.
Crews, agents and tasks, model and tool calls, tokens.
Agents, handoffs, tools and guardrails, for SDK 0.22.2 and later 0.22 releases.
Agents, sub-agents, tools and model calls. Also works deployed.
On your computer
Early accessClaude Code, Codex and Cursor keep running where you started them. The Sulcus command-line tool is provided on request, and controls work while the computer is online.
Deployed elsewhere
The agent keeps running where it is. Sulcus reads its telemetry, so runs appear after the fact and can’t be stopped from Sulcus.
Your ADK service sends its traces to Sulcus.
Sulcus reads your environment’s Application Insights telemetry.
Your own agent
PreviewAny agent can report its runs over a plain HTTP API, ask a person to approve an action and check whether someone asked it to stop. It has to call the API itself.
Custom agents docs