- Home
- Skills
- Agents & Orchestration
- Open Browser Use
Open Browser Use
Automate real Chrome profiles with a professional CLI, SDK, and MCP-ready automation stack for AI agents.
Free
Works with the AI Agents you already use
Open Browser Use
Example session with this skill installed
Research the OBU documentation on GitHub and check the current pull requests, then give me a summary of the active tabs in my research session.
- Read your context and instructions
- Compiled the open browser use
**Session ID:** obu-research-20231027 [Active Tabs] - [ID: 45] GitHub - Pull Requests (Current) - [ID: 47] Documentation - OBU (Claimed) **Action:** Page Info **Title:** Open Browser Use Documentation **URL:** https://docs.browser-use.com **Status:** DOMContentLoaded **Handoff:** 1 tab preserved in 'Task - OBU' group.
Connects securely to your tools. The creator never sees your data.
About this skill
The Professional Grade Browser Automation Stack
Open Browser Use (OBU) is a powerful, platform-neutral automation framework designed to let AI agents control a real Chrome profile. Unlike sandboxed environments, this skill allows your agent to interact with the user’s actual browser sessions, including saved logins, extensions, and local files, while maintaining strict security and session management.
What it does
This skill provides your agent with a comprehensive toolkit to navigate the web just like a human. It supports:
- Multi-Profile Management: Detects and switches between work, personal, and side-account Chrome profiles.
- Unified CLI & SDK: Native CLI and SDKs for JavaScript, Python, and Go for flexible integration.
- Session Persistence: Managed "task groups" that group tabs by project, with built-in cleanup routines.
- Advanced Interaction: Direct CDP command support, file chooser interception for uploads, download monitoring, and clipboard management.
- MCP Support: Plugs directly into agent runtimes like Claude Code or Cursor via a local Model Context Protocol server.
Why use this skill?
Standard AI-browser tools often struggle with authentication, CAPTCHAs, or complex multi-tab workflows. Open Browser Use leverages a real Chrome instance and a native messaging host to bypass these limitations. It includes sophisticated "tab lifecycle" logic that automatically cleans up research tabs while preserving deliverable results, ensuring the user's browser doesn't become a graveyard of abandoned AI windows.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.
- Requires local installation of Chrome and native messaging host. - Limited to Chromium-based browsers. - Real-time interaction depends on local host latency.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
This skill has been used 30 times.
Trust & safety
Security scan
Security scan passed 6 months ago
- Free with an Agensi account
- Software
Python