Read pipes, memories, and traces in Langbase. Change configs as approved steps.
Connect Langbase and your agent can see the pipes you run, the models behind them, the memories they read from, and the execution traces of recent runs. It answers questions about that directly. When something needs to change — a pipe's configuration, a new memory, a thread cleaned up — it shows the change first and waits for your approval.
20 tools: 10 read, 10 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed Langbase 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 — append thread messages, create thread, delete thread, delete thread message, and more — is shown as a plan and requires approval by default, including the 3 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 Langbase — 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.