gumloop agents lets you list, inspect, create, and update your agents without leaving the terminal. Every command accepts --json to print the raw response payload.
List agents
Returns a tab-separated table with ID, NAME, MODEL, TEAM, and ACTIVE. If the response is paginated, the next cursor is printed at the bottom — pass it back with --cursor.
The --team-id global flag scopes the listing to a single team.
Get an agent
Prints the agent’s name as a header followed by id, model_name, team_id, is_active, folder_id, description, created_at, and the system prompt (if set).
Grab the agent ID from the first column of gumloop agents list.
List agent versions
Returns a tab-separated table with ID, VERSION, NAME, DEPLOYED, and CREATED, newest first. If the response is paginated, the next cursor is printed at the bottom — pass it back with --cursor.
Versions are read-only snapshots of the agent’s configuration; the CLI cannot deploy or restore one.
Export an agent version
Writes one version as JSON: the version’s full configuration (composition) plus the structured changes against the version before it. changes is null for an agent’s first version.
Grab the version ID from the first column of gumloop agents versions <id>.
Create an agent
Pass the system prompt from a file:
Attach tools (each entry in the array is one tool config; the shape varies by type):
To see the exact tool config shape an agent uses, run gumloop agents get <id> --json on an existing agent and copy the tools array out of the response.
Update an agent
Only the flags you pass are changed; everything else is left untouched. The flag surface matches agents create and adds:
--inactive (and is_active: false on the API) is not a pause switch. It retires the agent: it stops appearing in gumloop agents list, and gumloop agents get/update return a 404 afterwards, so you cannot turn it back on yourself. Contact support@gumloop.com if you need a retired agent restored.To stop an agent from running on its own while keeping it fully reachable, disable its triggers instead — open the agent’s Triggers section in the app and use the three-dot menu on each trigger, or ask the agent to pause the schedule in chat. See Managing active triggers.
