hanzi-browse
CommunityControl a real browser in AI workflows.
Software Engineering#automation#session-management#web-testing#ai-agent#browser#ui-interaction#real-browser
Authorsharondevs
Version1.0.0
Installs0
System Documentation
What problem does it solve?
AI agents often struggle to interact with real browsers when tasks require rendered pages, authentication, form submissions, visual checks, or posts to live sites. Hanzi Browse provides a controlled bridge to the user's actual browser, enabling precise, authenticated automation within AI workflows.
Core Features & Use Cases
- Start and manage real-browser sessions with browser_start, including navigation, clicking, typing, and form filling.
- Maintain ongoing sessions with browser_message, status checks via browser_status, and safe error handling via browser_screenshot.
- Perform end-to-end browser tasks in real user contexts (e.g., login flows, test automation, posting content from authenticated accounts).
Quick Start
Run npx hanzi-browse setup to install the Chrome extension and MCP server.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: hanzi-browse Download link: https://github.com/sharondevs/job-auto-apply/archive/main.zip#hanzi-browse Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.