agent-browser-clawdbot-disabledHeadless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection
Install via ClawdBot CLI:
clawdbot install quanfuda/agent-browser-clawdbot-disabledGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/vercel-labs/agent-browserAudited Apr 18, 2026 · audit v1.0
Generated May 9, 2026
Use agent-browser to navigate to multiple websites, snapshot pages, and extract structured data like text, attributes, and HTML via ref-based selection. This is ideal for scraping product listings or news articles with deterministic element targeting.
Automate complex form workflows by filling inputs, selecting options, checking boxes, and submitting across multiple pages. Ref-based selection ensures reliable interaction even with dynamic content.
Simulate simultaneous user sessions with isolated browser contexts using the --session flag. Save and load authentication state to bypass login flows, enabling parallel testing of admin and user scenarios.
Continuously monitor e-commerce sites by navigating to product pages, taking snapshots, and extracting price text. Use wait commands for network idle to ensure accurate data capture.
Run a suite of interaction tests on web applications by clicking, filling, and verifying element states. Save screenshots on failure for debugging, and use sessions to isolate test environments.
Offer structured web data extraction pipelines to clients, using agent-browser's deterministic refs for reliable scraping and state persistence for scalable operations.
Provide a platform where customers upload automation scripts executed via agent-browser. Monetize through usage-based pricing for compute resources and session management.
Develop an internal testing framework using agent-browser's multi-session and state persistence to allow QA teams to run parallel regression tests, reducing manual effort.
💬 Integration Tip
Combine agent-browser with state save/load to skip authentication flows in repeated runs, and always use the --json flag on snapshots for easy parsing by AI agents or scripts.
Scored May 9, 2026
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.
Uses a headless browser to navigate web pages, interact with elements, and extract clean, readable text content from URLs.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection
通过已登录的Edge或Chrome浏览器，利用Chrome DevTools Protocol执行JS渲染页面的导航、点击、截图及数据提取等自动化操作。
High-performance browser automation for heavy scraping, multi-tab management, and precise DOM extraction. Use this when you need speed, reliability, or advanced state management (cookies/local storage) beyond standard web fetching.
Ultimate stealth browser automation with anti-detection, Cloudflare bypass, CAPTCHA solving, persistent sessions, and silent operation. Use for any web automation requiring bot detection evasion, login persistence, headless browsing, or bypassing security measures. Triggers on "bypass cloudflare", "solve captcha", "stealth browse", "silent automation", "persistent login", "anti-detection", or any task needing undetectable browser automation. When user asks to "login to X website", automatically use headed mode for login, then save session for future headless reuse.