Omniscio

AI Browser (in development — enable it in Settings → Lab) (part 2)

This second half of the AI Browser page covers what the feature added over the plain embedded browser — real tabs, a bookmarks bar and manager, browsing history, a download shelf, Find and the collapsed toolbar — plus spaces and quick navigation. It then documents the agent's own isolated tab: the MCP tool vocabulary that drives the page, the plan-approval queue, and the permission tiers that decide what it may do. The point-at-the-page pair, Design mode and Visual Edit, gets its own section.

On this page

What it is

This is part 2 of the AI Browser page. It carries what the feature added over the plain embedded browser, the two point-at-the-page tools (Design mode and Visual Edit), spaces and quick navigation, the panel's old agent tab — now retired, so every tab is yours — and the per-site permission tiers, which Agent Web reads and which are now set in Settings → Agent Web.

Where to find it

The feature lives in the Browser pane, opened from the Omniscio sidebar with the ai-browser Lab flag on; AI Browser covers the rest of it, including how to turn it on, the autofill vault, Memories, Journeys, side chat, skills, video pages, PDF pages and co-work. The panel's own controls named here sit in the Browser panel itself; the per-site tiers are set in Settings → Agent Web → Site rules, and whether the panel stays loaded in the background is set in Settings → Performance.

How it behaves

What you get (over the plain Embedded Browser)

  • Real tabs. A tab strip across the top — open, switch, and close as many pages as you like, each its own web view. window.open() / target="_blank" links open as a new in-app tab instead of being blocked.
  • A bookmarks bar + manager. Click the star in the address bar to bookmark the current page; bookmarks show as a bar under the toolbar. The Manage button opens a modal to rename, reorder, and remove them.
  • Browsing history. Pages you visit in your tabs are recorded; the History button opens a modal with five tabs — History (click to reopen, "Clear browsing history" with confirmation), Memories, Passwords, Journeys, and Skills — the last four are covered in their own sections. The address bar suggests from your history + bookmarks as you type.
  • A download shelf. Downloads appear in a strip at the bottom with progress, "show in folder", and discard. A file type that can run code prompts you to approve before it saves.
  • Find in page (in the ⋯ overflow menu or Ctrl+F), zoom (Ctrl +/−/0), and the usual keyboard shortcuts (Ctrl+T new tab, Ctrl+W close, Ctrl+L address bar, Ctrl+R reload).
  • A collapsed, progressive-disclosure toolbar. At rest the address bar's right side shows just four controls — ✨ AI tools (the four page-action modes below), side chat, Library (the History/Memories/… hub), and a ⋯ overflow (Find, command palette, open-in-new-window, tab-strip orientation) — plus the bookmark star inside the address bar. A Stop control surfaces while you're recording.
  • Point-and-prompt Visual Edit. The Visual edit item in the ✨ AI tools menu lets you click any element on the page and describe a change ("make this button blue"); if you have a session bound in the side chat, Omniscio sends the request straight to it — no copy-paste needed. With no session bound, it falls back to copying the same prompt to your clipboard. A separate Design mode tool goes further — see Design mode & Visual Edit below.
  • Spaces, a command palette, and quick tab switching. Tab groups, Ctrl+K search, and Ctrl+Tab most-recently-used cycling — see Spaces, tabs, and quick navigation below.

Every tab is yours (the agent's tab is retired)

Every tab in the strip is one of your tabs — normal browsing on the same persist:browser cookies as the plain Embedded Browser (so your logins carry over), each with its own close button. A link that opens a new window opens as another of your tabs.

The strip used to end in a fixed agent's tab — an unclosable tab on a separate, isolated profile, built for an Omniscio agent to drive through an agent tool route (POST /ai-browser/tool) and a bundled MCP server of browser_* tools. That route and those tools are retired: every agent now browses in its own Agent Web browser (amc-web), a real Chrome private to its session, with its own sign-ins, site rules and approval cards. With nothing left driving it, the agent's tab is retired too, along with the things that only served it:

  • The tab itself, and the extra unclosable tabs a link inside it used to open.
  • "Use in app → sign the Agent tab in with this login" in Settings → Browser Logins. Use in app now just opens one of your tabs already signed in with that login, on its own per-login space kept apart from your normal browsing — see Browser Logins.
  • The "Keep the Browser loaded in the background" switch in the History modal's Permissions tab, which was the last thing in that tab, so the tab is gone too. The Browser still stays loaded when you switch to another view, so your tabs keep their pages: it now follows Settings → Performance → "Keep recently-opened panels loaded" (Keep panels loaded), on by default — turn that off and the Browser reloads its pages when you come back.

Per-site permission tiers (what Agent Web may do on a site)

In Settings → Agent Web → Site rules (they moved there from this panel's old History → Permissions tab, so turning the panel off never hides them), set an exact permission for any site: control (the default — an agent can read and act), read-only (an agent can read the page but any action is refused), no-access (an agent can't even read it), or blocked (same effect as no-access, meant for sites you never want an agent touching, like your bank). Adding a bare domain (no subdomain) covers all its subdomains too. Agent Web reads this table on every agent browser command, and a finance, payment or social site you have not set a rule for asks you on a card before an agent acts on it — see Agent Web. (Don't confuse this with the tab right-click menu's Pin/Favorite/Today — that's tab housekeeping, not permissions; see Spaces, tabs, and quick navigation.)

The panel's other agent controls — the Pause button and its "you have control" banner, the agent-control and allow-list settings, the attended-only-writes check, the "Let the agent act while I'm watching" supervised-writes switches, and co-drive (the toolbar's "Let AI co-drive this tab" toggle, its "You're driving" pill and the "Let AI co-drive my browser tabs" switch in Settings → Browser Logins) — governed the retired agent tool route. With no agent driving the panel they governed nothing, so they are removed; Agent Web has its own controls. A value an older install saved for one of them stays in its settings file, unread.

Design mode & Visual Edit

Two point-at-the-page tools, both for your own tabs (not the agent's), both items in the ✨ AI tools menu next to the address bar:

  • Visual edit (in the ✨ AI tools menu) — click an element, type what you want changed in plain English ("make this button blue"), submit. With a session bound in the side chat, Omniscio sends it the element's selector, its rendered HTML/styles, and a cropped screenshot, with an instruction to make the change in the source code. With no session bound, it falls back to copying that same prompt to your clipboard so you can paste it in yourself.
  • Design mode (in the ✨ AI tools menu) — click an element and a live style panel opens: color, background, font size/weight, padding, margin, width, height, and border radius, all editable, plus buttons to move the element up or down among its siblings (button-stepped, not drag-and-drop). Changes preview instantly on the real page so you can see what you're doing — but nothing here is saved to the page itself. Apply needs a session bound (there's no clipboard fallback for Design mode); it packages only what changed — the before/after value of each property you touched, plus how many positions you reordered it — and sends that delta to the session with an explicit instruction to map it onto the component's source and edit the source, never the running page. Design mode tells the agent to edit your code; it does not hack the live page.

Both hand off to whichever session is currently selected in the browser's side chat pane — neither spawns a new one.

Spaces, tabs, and quick navigation

  • Spaces. A space is a named group of tabs — not a separate profile or login, just a way to keep "work" tabs and "research" tabs apart. Create, rename, or delete one from the space switcher (next to the tab strip, or inline at the top of the vertical tab rail); switching spaces swaps which tabs are visible.
  • Vertical tab strip. A toggle in the ⋯ overflow menu swaps the horizontal tab strip for a vertical one down the side — same tabs, same behavior, just a different layout. Your choice is remembered.
  • Tab housekeeping (Pin / Favorite / Today). Right-click a tab for Pin (never auto-sleeps, discards, or archives), Favorite (exempt from auto-archiving only), or leave it Today (the default — eligible for Omniscio's normal inactive-tab cleanup). This is unrelated to the per-site permission tiers above despite the similar name — it's about memory/tab-count housekeeping, not what an agent is allowed to do. The active tab and the agent's tab are never auto-cleaned.
  • Command palette (Ctrl+K). Fuzzy-search across every open tab (in any space), your bookmarks, and your history, plus quick actions: new tab, new space, "ask about all open tabs" (hands every open tab's URL and title to the active chat session as context), and toggling the side chat.
  • Most-recently-used switching (Ctrl+Tab). Hold Ctrl and tap Tab to cycle open tabs most-recently-used-first, the same feel as Alt+Tab for windows; release Ctrl to land on the one you want.

This page is the companion to AI Browser, which carries the rest of this feature. Agents browse in Agent Web. The road for driving a browser you are signed into yourself is My Real Chrome and Browser Logins; the plain single-page pane it built on is Embedded Browser.

Last verified 2026-10-06