domains / families / agent-tooling / agent-browser
Browse the web for any task — research topics, read articles, interact with web apps, fill forms, take screenshots, extract data, and test web pages. Use whenever a browser would be useful, not just when the user explicitly asks. A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
The copies share the same core agent-browser CLI workflow (open, snapshot -i, interact via @refs, re-snapshot), but each adds material steps or constraints the others lack. am-will/codex-skills adds real Chrome profile/CDP reuse and headed manual login for OAuth. LeoYeAI/openclaw-master-skills adds video recording, browser settings (viewport/device/geo/offline/headers/credentials/media), and more complete cookies/storage commands. brycewang-stanford/Auto-Empirical-Research-Skills adds command chaining guidance, state save/load with encryption, session management, and connecting to an existing Chrome instance. FreedomIntelligence/OpenClaw-Medical-Skills is a shorter variant with similar core commands but lacks the unique additions above. Crowning one copy would hide real alternatives for authentication, recording, state persistence, and chaining.