Skip to main content
  1. Home
  2. Computing
  3. News

1Password lets Claude inside your accounts without handing over the keys

Claude can now sign in on your behalf while your password stays hidden, though trusting it after login is a separate decision

Add as a preferred source on Google
1Password official
1Password

1Password is giving Claude a way into your online accounts without making your passwords part of the bargain. The new 1Password for Claude integration can fill login details while keeping the credentials hidden from Anthropic’s AI agent.

Available now on Mac, the feature kicks in when Claude reaches a sign-in page during a task. Claude requests a saved login, then you approve or deny it. If approved, 1Password submits the credentials through a separate encrypted channel. Passwords and one-time codes never enter Claude’s context or Anthropic’s systems.

How does 1Password keep Claude out

Claude identifies the website and asks for access, but it receives only basic information about the approved login and whether the attempt worked. The 1Password browser extension decrypts and inserts the password while Claude temporarily stops reading the page.

Agentic Mode also switches on whenever Claude takes control of a browser tab. It removes 1Password’s usual autofill interface and limits the agent to vault items approved for that session. If the submission fails, the extension clears the credentials before Claude regains control. There’s no half-filled form waiting for an inquisitive AI to inspect.

Where does that protection end

These safeguards cover how credentials are approved and delivered. Once Claude successfully signs in, it can operate inside the account as an authenticated user. What happens next depends on Claude’s controls and whatever that website allows it to do.

Recommended Videos

Keeping a password away from the model closes one obvious security hole. It doesn’t make every action after login harmless. You’ll still need to consider the task and what Claude could view or change inside that account. A secure login solves the credential problem, not the trust problem.

Who can use it now

1Password for Claude is available to individual, family, and business subscribers using a Mac. It requires version 8.12.28 or later of the 1Password desktop app and browser extension, plus Claude’s desktop and browser extensions. Business administrators must enable agentic autofill before employees can connect it.

The first release works with usernames, passwords, and one-time codes saved as login items. Passkeys and social options such as Sign in with Google aren’t supported yet. Start with a tightly defined task on a low-risk account before giving Claude access to anything that could become expensive, public, or painful to undo.

Paulo Vargas
Paulo Vargas is an English major turned reporter turned technical writer, with a career that has always circled back to…
New open-weight AI from China is toppling the best of OpenAI and Claude Fable
Moonshot’s 2.8-trillion-parameter Kimi K3 beats Fable 5 and GPT 5.6 Sol in select benchmarks
Art, Drawing, Plant

China's Moonshot AI has launched Kimi K3, a massive 2.8-trillion-parameter model built for coding, research, reasoning, and visual tasks. Moonshot admits K3 still trails Claude Fable 5 and GPT 5.6 Sol overall. Even so, its benchmark results put it surprisingly close to both, and it finishes ahead in several tests.

How close is Kimi K3 to the best closed models?

Read more
Gemini could finally let you choose how friendly it sounds
Finally, you can stop Gemini from sounding like your HR manager
Google Gemini

Google has spent the past few months making Gemini sound more natural, expressive, and conversational. Now, it appears the company is preparing to give users far more control over how the AI speaks.

Code spotted by Android Authority's APK Insights - the latest beta version of the Google app suggests Gemini may soon allow users to customise its voice across four separate parameters: Energy, Formality, Warmth, and Speed. Instead of choosing from a fixed list of personalities, users could tweak these characteristics to create a voice that better suits their preferences.

Read more
ChatGPT will now remind teens to take breaks and give parents more controls
New parental controls include Quiet Hours, Study Mode defaults, and alerts for serious account violations.
chatgpt-teen-safety-features

OpenAI wants to make ChatGPT safer for teens, and the changes go well beyond a simple content filter. In a new update, the company laid out its stance on why teens should have access to AI in the first place, arguing that keeping them away from it entirely would leave them unprepared for one of the defining technologies of their generation.

Nearly 90% of teens already use ChatGPT weekly for learning, research, or getting organized, which is why OpenAI says access needs to come paired with real protections built for their age.

Read more