Inspect Replicate deployments and models, then change them as approved steps
Connect Replicate with an API key and Luumen can read your account's deployments, models, hardware SKUs, files, and prediction history on request. Ask what a deployment is running or why a prediction stalled, and get an answer from the live API. Changes — new deployments, predictions, training jobs, metadata edits — are previewed and held for approval before they run.
30 tools: 19 read, 11 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed Replicate run looks like inside Luumen.
Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.
Read actions answer immediately. Anything that writes — cancel prediction, create model, create prediction, create deployment, and more — is shown as a plan and requires approval by default, including the 4 actions classified as destructive. Administrators configure that per tool, so you decide exactly which actions can ever run unattended.
You decide. Actions are granted per agent, skill, and team, and per environment — production is not staging. Read access can be broad while writes stay narrow.
Every call to Replicate — read or write, approved or declined — is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.
Connect in minutes. Every action scoped, approved, and audited from day one.