Drive headless browsers, inspect sessions, and ship automation tasks from the terminal
Anchor Browser runs the browser automation behind your web-facing runbooks. Connect it and Luumen can read session state, page lists, rendered page content, and task versions while you work. When a task needs to change — a new draft, a deploy, a fresh profile — Luumen shows the plan first and waits for your approval before writing. Authentication is by API key.
64 tools: 25 read, 39 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed Anchor Browser 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 — click mouse, create integration, create or update task draft, create profile, and more — is shown as a plan and requires approval by default, including the 7 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 Anchor Browser — 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.