gbrain

Sign in

Page fetching

Page fetching from the command line.

Turn a URL into readable text, including pages that need a browser.

For the agenda PDF, the council minutes, the pricing page that renders in JavaScript. One command in, text out, on the same record as everything else.

Four commands

Each of the last three opens a browser tab, does one thing, and hands the terminal back.

$ curl -sSL https://gbrainio.terminalwire.sh | bash   # install it
$ gbrainio login                                      # name this terminal, pick how long it lasts
$ gbrainio auth grant firecrawl                       # connect the account
$ gbrainio permission                                 # turn Page fetching on

The installer is a shell script. Read it first. macOS and Linux.

Then these

Read from the tool plane, so this list is what the CLI answers to today. Add -h to any of them for its arguments.

gbrainio tool firecrawl search: Search the web (Firecrawl)
gbrainio tool firecrawl scrape: Read a page

Same tools, any assistant

Claude Code, Cursor and Codex reach the same Page fetching through MCP, on the same permission and the same record.

Page fetching over MCP

How the whole thing fits

One permission, one daily ceiling, one record, across every client that asks.

Also on the plane

Gmail Search, read, file and draft mail from a terminal or an assistant.
Google Calendar List, add, change and cancel events without leaving the terminal.
Web search Search the live web and get back text, not a page of links.
Google Drive Not yet Not connected yet.