README
¶
Open Browser Use
open-browser-use is a browser automation layer that stays neutral across
agent runtimes. It is also an open-source alternative to the Chrome Browser Use
capability recently shipped in Codex.app. For the story behind it, see the
Browser Use deep dive.
Under the hood, it pairs a browser extension with the open-browser-use CLI.
You can integrate it through the JavaScript SDK, the Python SDK, or the CLI.
Quick Start
brew tap iFurySt/open-browser-use
brew install open-browser-use
open-browser-use setup beta
Install the CLI
# npm
npm i -g open-browser-use
# Homebrew
brew tap iFurySt/open-browser-use && brew install open-browser-use
# Upgrade
brew upgrade open-browser-use
Set Up Chrome
Register the native host for the extension, then install the matching Chrome extension.
# The Chrome Web Store listing is still under review, so skip this for now.
# open-browser-use setup
# Install from the zip/crx package instead. Drag the opened package into
# chrome://extensions/.
open-browser-use setup beta
You can also download the latest package directly from GitHub Releases and install it manually.
Use It
Install the skill directly:
# Install for Codex
npx skills add iFurySt/open-codex-browser-use -g -a codex --skill open-browser-use --copy -y
npx skills ls -g -a codex | rg 'open-browser-use'
codex exec "Use open-browser-use to check today’s Hacker News and summarize the most worth-reading posts."
# Install for Claude Code
npx skills add iFurySt/open-codex-browser-use -g -a claude-code --skill open-browser-use --copy -y
You can also manually download and install the
open-browser-use skill, then start using it from
your agent.
Downloadable .skill and .zip packages are available in
GitHub Releases.
MCP
Agent runtimes with local MCP stdio support can run Open Browser Use directly:
[mcp_servers.open_browser_use]
command = "obu"
args = ["mcp"]
The server exposes browser tools for tab listing, opening, claiming, navigation, CDP, action plans, and cleanup.
Directories