Let AI Search, Read, and Work on Web Pages

Server-side search and browsing usually come from shared data-center IP addresses. Sites often answer that traffic with CAPTCHAs, rate limits, or outright blocks. Cumbersome sends the request from your own network and a real WebKit browser on your iPhone, iPad, or Mac. The site sees your network's IP address and the browser characteristics of an actual device instead of a generic cloud crawler.

It's private by architecture. Your device connects directly to the search engine or website. Folding Sky never proxies the request or receives the query, URL, or page contents through a backend. The search engine or site still sees the request, and your selected AI provider receives the result snippets or extracted text it needs to answer.

Web Agent keeps the current page and browsing history with the active chat. You can watch the page, scroll or type yourself, take over when a site needs human input, and then let the model continue from the same page.

The browser uses a nonpersistent WebKit data store. Closing Web Agent, disabling it, or leaving the chat discards that session. This limits what remains on the device afterward. It does not stop a website or your selected AI provider from receiving information while the session is open.

Local Web Search takes search terms and returns result titles, URLs, and snippets. Choose DuckDuckGo, Bing, or Baidu as your Preferred Search Engine in Settings. Cumbersome tries it first for every search.

If it times out or returns an unusable results page, Cumbersome tries the others. Each gets up to eight seconds. Baidu stays last unless you choose it first. The tool row names the engine that worked and tells you when Cumbersome used a fallback.

Local Web Browser starts with an exact URL. It opens that page through your device and returns readable page text to the AI. It works whether Local Web Search is on or off.

When a page needs an interaction before its content appears, Local Web Browser can run JavaScript once after loading and before reading the page. This works in visible and headless modes.

Use Web Agent when the work takes several steps or you want to interact with the page. Local Web Search and Local Web Browser start fresh for each request and can run without an open browser window. With both enabled, the model can search first and read the useful results instead of relying on snippets.

Headless mode can handle up to three independent searches or page loads at once. Web Agent stays sequential because each action depends on the state left by the one before it.

Each search, page open, and extraction appears as a tool event. The result is easier to audit because you can see which sites contributed to the answer. This is especially useful for research that requires several sources rather than a single opaque search summary.