Get the newsletter
Google · AI / ML · Filed Jun 11, 2026 · USPTO published Oct 1, 2026 · Oct 1 release

Google Patents a Browser That Remembers Every Page You Visit and Lets You Search Them with Plain English

Google is patenting a browser that converts every web page you visit into a kind of personal searchable archive, so you can ask it questions about your own browsing history the same way you'd ask a person.

A browser interface displays a natural language query about trees and offers options for starting a conversation or performing a web search. Drawing from patent filing US 2026/0300422 A1.
A browser interface displays a natural language query about trees and offers options for starting a conversation or performing a web search.All 26 drawings ↓
Publication number
US 2026/0300422 A1(US20260300422A1)
Applicant
Google LLC
Filed · Published
Jun 11, 2026 · Oct 1, 2026
Inventors
Zebedee Pedersen, Yasmine Rubinovitz
Status when we published
Waiting for an examiner
Document
20 claims
US classification
707/722
Parent application
Continuation of 18/982,645 (filed Dec 16, 2024)(18982645)

What Google's AI-memory browser actually does for you

A person opens a dozen tabs over the course of a day, reads half of them, closes a few, forgets most. Later, they can't remember which article had that specific statistic or which product page listed the return policy. That's the problem Google is trying to solve here, and it involves building a memory system directly into the browser.

The patent describes a browser that automatically converts the content of every page you visit into a format an AI can search and reason over. Instead of just keeping a list of URLs in your history, the browser stores the actual meaning of the content, so you can later ask something like "what did I read about sleep last week?" or "open that page where the price was under $50" and get a useful answer.

Vector database is the technical term for the memory system doing the heavy lifting here. Think of it as a filing cabinet where each page gets stored not as raw text but as a kind of fingerprint that captures its meaning, making it possible to find things by concept, not just by keyword.

From the filing · CLAIM 1
… determining, using a vector database representing session data associated with the browser application, session data descriptive of at least one of: a web browsing history, or a current state of the browser application; …

Translation: The browser uses a specialized database to track everything you visit and what you are currently doing.

How the vector database turns web pages into searchable memory

The core idea is that as you browse, the browser feeds each page's content into a machine-learning model that converts it into a vector embedding (a list of numbers that encodes meaning and context, not just words). Those embeddings are stored locally in a vector database tied to your browser session.

When you type or speak a query, the browser doesn't run a keyword search. Instead, it converts your question into the same kind of numerical fingerprint, then finds stored content with similar fingerprints. This is how it can match the concept behind your question to pages you visited, even if your wording doesn't match anything on those pages.

  • Session data storage: The database tracks browsing history and the current state of open tabs, not just URLs.
  • Multi-modal search: The patent mentions searching across multiple types of content, meaning text, images, and potentially other formats.
  • Sequence processing model: A language model (similar to the kind behind chatbots) takes your query plus the retrieved content and constructs an actual answer or browser action.

The output isn't always a text answer. The browser can also use the response to modify its own state, meaning it could navigate to a page, reopen a tab, or fill a form based on what you asked.

From the filing · THE ABSTRACT
A user can query the web browser using simple instructions. The web browser can interpret the instructions and use the embedded data store to quickly search across multiple modalities of embedded data to retrieve relevant results.

Translation: You can ask the browser plain questions to instantly search your past web activity.

What this means for how you find things you've already read

If this ships in something like Chrome, it changes the basic relationship between you and your browser history. Right now, your history is a timestamp log that tells you what you visited but can't help you find what you actually learned or saw. A browser with this system would let you treat your own browsing the way you treat a conversation with a knowledgeable assistant, asking it things like "what were the ingredients on that recipe I found Tuesday" or "remind me what that article said about interest rates."

the pattern in Google's AI-in-everyday-tools filings points toward baking AI capabilities into products people already have open all day rather than asking them to switch to a new app. Whether this ever reaches a consumer release is a different question, but the direction is clear: the browser as a memory layer, not just a window to the web.

Google's 33rd filing we've tracked since May on AI assistants that remember you follows one on remembering shared images and one on learning formatting habits, adding another application for AI that holds onto personal details.

Source: US 2026/0300422 A1 at the USPTO (PDF). Full patent text and figures are in the official publication.

Get our take in your Top Stories

Liked this breakdown? Add Patentlyze as a preferred source on Google, and our plain-English take shows up more often in your Top Stories the next time Google patent news breaks.

There are more where this came from

We read every patent application Big Tech publishes and send you the ones worth knowing. Plain English, free, every week.

The drawings · 26 sheets

26 drawing sheets from US 2026/0300422 A1 · click any drawing to enlarge

Machine learning system overview., drawing sheet 1 from US 2026/0300422 A1
Sheet 1 Machine learning system overview.
Session data processing and storage., drawing sheet 2 from US 2026/0300422 A1
Sheet 2 Session data processing and storage.
Interaction trajectory prediction model., drawing sheet 3 from US 2026/0300422 A1
Sheet 3 Interaction trajectory prediction model.
Preprocessing query to machine learning., drawing sheet 4 from US 2026/0300422 A1
Sheet 4 Preprocessing query to machine learning.
Vector query to embedded data., drawing sheet 5 from US 2026/0300422 A1
Sheet 5 Vector query to embedded data.
Identified data to machine learning., drawing sheet 6 from US 2026/0300422 A1
Sheet 6 Identified data to machine learning.
Inputs to primary machine learning., drawing sheet 7 from US 2026/0300422 A1
Sheet 7 Inputs to primary machine learning.
Postprocessing query to machine learning., drawing sheet 8 from US 2026/0300422 A1
Sheet 8 Postprocessing query to machine learning.
Show the other 18 sheets
Google Patents a Browser That Remembers Every Page You Visit and Lets You Search Them with Plain English patent drawing, sheet 9
Sheet 9
Google Patents a Browser That Remembers Every Page You Visit and Lets You Search Them with Plain English patent drawing, sheet 10
Sheet 10
Google Patents a Browser That Remembers Every Page You Visit and Lets You Search Them with Plain English patent drawing, sheet 11
Sheet 11
Google Patents a Browser That Remembers Every Page You Visit and Lets You Search Them with Plain English patent drawing, sheet 12
Sheet 12
Google Patents a Browser That Remembers Every Page You Visit and Lets You Search Them with Plain English patent drawing, sheet 13
Sheet 13
Google Patents a Browser That Remembers Every Page You Visit and Lets You Search Them with Plain English patent drawing, sheet 14
Sheet 14
Google Patents a Browser That Remembers Every Page You Visit and Lets You Search Them with Plain English patent drawing, sheet 15
Sheet 15
Google Patents a Browser That Remembers Every Page You Visit and Lets You Search Them with Plain English patent drawing, sheet 16
Sheet 16
Google Patents a Browser That Remembers Every Page You Visit and Lets You Search Them with Plain English patent drawing, sheet 17
Sheet 17
Google Patents a Browser That Remembers Every Page You Visit and Lets You Search Them with Plain English patent drawing, sheet 18
Sheet 18
Google Patents a Browser That Remembers Every Page You Visit and Lets You Search Them with Plain English patent drawing, sheet 19
Sheet 19
Google Patents a Browser That Remembers Every Page You Visit and Lets You Search Them with Plain English patent drawing, sheet 20
Sheet 20
Google Patents a Browser That Remembers Every Page You Visit and Lets You Search Them with Plain English patent drawing, sheet 21
Sheet 21
Google Patents a Browser That Remembers Every Page You Visit and Lets You Search Them with Plain English patent drawing, sheet 22
Sheet 22
Google Patents a Browser That Remembers Every Page You Visit and Lets You Search Them with Plain English patent drawing, sheet 23
Sheet 23
Google Patents a Browser That Remembers Every Page You Visit and Lets You Search Them with Plain English patent drawing, sheet 24
Sheet 24
Google Patents a Browser That Remembers Every Page You Visit and Lets You Search Them with Plain English patent drawing, sheet 25
Sheet 25
Google Patents a Browser That Remembers Every Page You Visit and Lets You Search Them with Plain English patent drawing, sheet 26
Sheet 26
Patent filing page

More in AI assistant & agent

All 436 AI assistant & agent patents →

Watchlists this filing belongs to

All watchlists →
Reader comments

No comments yet

Start the discussion

Real name or a handle, either is fine. Comments are read by a person before they appear, so allow a little time. Keep it about the filing.