1Password lets AI agents use your passwords without seeing them

1Password is introducing a new feature that allows AI agents to sign into your accounts without actually seeing or handling your passwords. The aptly named 1Password for Agents doesn’t give bots free reign to access all of your connected accounts — you’ll still need to grant approval for sign-in requests — but should make it less cumbersome to use Agents for tasks that require them to log into various services. ”Agents are starting to do real work on our behalf. The old model where you hand over a credential and hope for the best doesn’t work,” 1Password CEO Aashish Tripathi said in a press statement. “An agent should be able to do the job it’s been asked to do without getting permanent access to everything behind the account, and 1Password provides the trust layer that makes this possible across personal agent experiences.” With this new system, an AI agent uses a unique digital key to verify its identity to 1Password when it reaches a sign-in form. The app then sends you a notification about which account credentials it needs, and why. If you choose to approve the request, 1Password will fill in the required login information instead of handing it to the agent. Approvals are granted on your own device to ensure you’re behind the permissions, making this a similar process to two-factor authentication. After the agent is signed in, it’ll continue with its task, without ever having actually seen your password. [Media: https://www.youtube.com/watch?v=-1SE6cBbeZg] This 1Password access system is designed to work with a variety of popular AI agents, including Meta Muse, ChatGPT Work and Dots, Claude Duet, Grok Bot, and Town. 1Password says more partners are working to bring support to 1Password for Agents, including Browserbase, Browser Use, Dana, Instinct, Kernel, Perplexity, Ramp, Tomo, and Wajo, with “additional integrations to come.”