1Password is introducing 1Password for Agents, a feature that lets AI agents sign in to accounts without seeing or handling passwords. Agents cannot access every connected account at will. Users must approve each sign-in request.
When an agent reaches a sign-in form, it uses a unique digital key to verify its identity to 1Password. The app then notifies the user which account credentials the agent needs and why. If the user approves the request, 1Password fills in the login information instead of giving it to the agent.
Approval happens on the user’s own device, a process similar to two-factor authentication. Once signed in, the agent can continue its task without having seen the password. The system is intended to make tasks involving logins less cumbersome while keeping each request subject to user approval.
“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 chief product officer 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.” A correction issued October 22 identified Tripathi as chief product officer, rather than CEO.
Multiple AI agents support the feature
1Password for Agents is designed to work with Meta Muse, ChatGPT Work and Dots, Claude Duet, Grok Bot, and Town. That range of agents reflects the feature’s aim to support sign-ins across different services without handing credentials to the agent doing the work.
1Password says Browserbase, Browser Use, Dana, Instinct, Kernel, Perplexity, Ramp, Tomo, and Wajo are also working to add support. The company says “additional integrations to come.”
