3 items
One chat, every AI model. It reads the page you are on, acts on it when you ask, and shows what each answer cost. Switchboard Agent puts a chat panel next to the page you are reading, and lets it act on that page when you ask. Ask a question and you get an answer. Ask for something to be done — "summarise this thread", "find the cheapest option in this list", "fill this form" — and the agent reads the page, works in small steps, and tells you what it did. WHAT MAKES IT DIFFERENT One chat, every model. You never pick a model. Each message is routed to the cheapest model actually capable of it, and every answer shows what it cost. It asks before it acts. The agent cannot touch a site until you allow that site, one site at a time. Anything that spends money, sends, posts or deletes stops and asks first — and the confirmation shows the literal action, never the model's description of it. It tells you when it fails. A click a site quietly ignored is reported as ignored, not as done. Your history stays on your machine. Conversations are stored locally in the browser. Page content is sent to the exchange only for the step that needs it. HOW TO USE IT 1. Create an account at switchesboard.com and copy your API key. 2. Click the Switchboard icon to open the side panel, paste the key. 3. Open any page and ask for what you want. REQUIRES AN ACCOUNT Switchboard Agent is a client for the Switchboard exchange. It needs an account at switchesboard.com with credit on it.
Aug 27, 2026
rating_count is the Chrome Web Store ratings count, not a written-review count.
Media assets
Screenshots and videos on the listing.
Has promo video
Whether the listing includes at least one video.
Languages
Declared language locales.
Developer website
Listing exposes a developer website URL.
Contact email
Listing exposes a contact email.
Keyword in name
Case-insensitive substring match in the name.
Keyword in description
Case-insensitive substring match in the description.
Keyword occurrences in description
Count of case-insensitive occurrences in the description.
Category user-count percentile
Share of same-category extensions with fewer users (null if unknown).
These are transparent listing completeness / keyword signals, not a prediction of Chrome Web Store search ranking.