Ask questions about your codebases, and add new repositories for analysis
Entelligence indexes GitHub repositories and answers questions about them. From the terminal, you can ask how a service handles retries, where a config value is read, or which module owns a failing path — without opening an editor. Adding a new repository for analysis runs as an approved step. No credential to set up.
2 tools: 1 read, 1 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed Entelligence run looks like inside Luumen.
Entelligence needs no credential of its own, so there is nothing to authorize. Access is still granted per agent, skill, and team inside Luumen, and every call is logged.
Read actions answer immediately. Anything that writes — add a new repository — is shown as a plan and requires approval by default. 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 Entelligence — 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.