browserclaw
CommunityControl live pages with snapshot-guided actions.
Software Engineering#playwright#web-testing#snapshot#browser-automation#ref-based#automation-patterns#interactive-browsing
Authoridan-rubin
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Browsers are hard for AI agents to control directly; BrowserClaw provides a deterministic, snapshot-driven interface that lets automation agents perceive page content through text snapshots and act via numbered refs.
Core Features & Use Cases
- Snapshot-based element targeting with numbered refs
- Navigate, click, type, select, and extract data from dynamic sites
- Re-snapshot after each action to maintain accurate context for decision-making
Quick Start
Launch a live browser, take an initial snapshot with interactive mode, and use the returned refs to drive actions.
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: browserclaw Download link: https://github.com/idan-rubin/browserclaw/archive/main.zip#browserclaw 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.