Search the Internet Archive, read item metadata, and stage file changes
Connect Archive.org and the agent can search the collection, pull item metadata, check Wayback captures, read view counts and referrers, and inspect IIIF images. Reads come back right away. Changes to item files, metadata, derivation, and your own reviews are previewed and sent for approval first. Luumen authenticates with an API key.
26 tools: 19 read, 7 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed Archive.org 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 — copy item file, delete item file, delete my archive.org review, derive archive.org item, 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 Archive.org — 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.