Skip to content

Browser Use Terminal

by Browser UseAgentGet organised

Runs browser tasks from a terminal screen where you can watch, steer and resume the agent

View on GitHub

About Browser Use Terminal

Browser Use Terminal is a terminal app where an AI agent carries out browser tasks for you in Chrome, with live controls to watch, steer, stop and resume the work.

For Terminal usersPeople who automate web chores

Made by Browser Use

Browser Use publishes this app as open source under the MIT license.

Stars
★ 662
License
MIT
Cost
Usage-based
Platforms
Mac · Linux
Level
Intermediate

Overview

Browser Use Terminal is a text-screen app for browser agents. You type a task such as finding a cancellation policy, and the agent drives Chrome while you watch, steer, stop or resume it. It can use your signed-in Chrome, a headless Chromium or the Browser Use cloud browser, and it keeps local history, screenshots and files for each task. It suits people comfortable with a terminal who want web chores done for them.

You can watch the agent work, step in at any moment and pick the same session up again later.

Try these first

Start with the first one: it is a small task you can check easily.

  1. Go to [website] and list the main headings on the page. Don't sign in.First try · read-only

  2. Find the cancellation policy for my current hotel reservation.uses your logins

  3. Open my company's dashboard and summarize failed jobs from today.uses your logins

  4. Log in to the vendor portal and download the latest invoice.downloads files

Example prompts written by Agent Flows Hub.

Features

From the creator's documentation.

FeatureWhat it doesRuns
Watch and steerRun browser tasks from a terminal screen and watch, steer, stop, retry and resume themYour computer
Browser choiceWork in your logged-in Chrome, a headless Chromium or the Browser Use cloud browserYour computer or cloud
Task historyKeeps local history, screenshots, artifacts and follow-ups for each taskYour computer
Saved loginsStores website passwords and 2FA setup keys for the agent, or imports them from 1PasswordYour computer
Assistant skillRegisters a skill so Claude Code, Codex or OpenCode can drive the same browserYour computer
Model providersSign in to a provider or use its API key, such as OpenAI or AnthropicModel provider

Good to know

You want an agent to finish a web chore while you stay in the terminal. Browser Use Terminal runs the task in Chrome, shows its progress live, and lets you steer, stop, retry or resume it.

Limits

  • It can work in your real, signed-in Chrome, so an agent can act as you on sites where you are logged in. Choose the local, headless or cloud browser before the first task.
  • Native Windows is not supported yet; the setup page says to use WSL.

Notes by (original project name: Browser Use Terminal), written from the creator's documentation, not from running it ourselves. Browser Use Terminal: README · Browser Use Terminal: documentation

Stuck setting it up?

Tell us what happened. We take a look first; if it needs paid work, you get an estimate before anything starts.

Get help

Other agents

  • BrowserOS Gives you a Chromium-based browser with an AI agent in every new tab
  • Cindy Hands work on your computer to an AI agent you can reach from your desktop or phone
  • Claude Code Lets you hand coding tasks to Anthropic's AI agent in your terminal, editor or desktop app
  • Claude in Chrome Lets Claude read pages in Chrome, then click, type and fill in forms for you
  • Codewhale Lets an AI agent in your terminal edit your code and run commands, with any model
  • Codex CLI Lets you hand coding tasks to OpenAI's agent, which edits and runs code on your computer

See all 69 agents · Install your first AI agent

GitHub