agent-browser-clawdbot-0Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection
Install via ClawdBot CLI:
clawdbot install auroechan/agent-browser-clawdbot-0Grade 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 16, 2026 · audit v1.0
Generated May 12, 2026
A market research firm uses agent-browser to automate extraction of competitor pricing, product descriptions, and reviews from e-commerce sites. The accessibility tree snapshots ensure deterministic element selection, even with dynamic content, reducing manual work by 90%.
A SaaS company tests their web application simultaneously from admin and user perspectives using isolated browser sessions. They automate login flows, state persistence, and snapshot comparisons to detect UI regressions across roles.
A sales team automates data entry into a web-based CRM by having the agent navigate, fill, and submit forms repeatedly. State persistence skips logins, and wait commands ensure page stability before interactions.
A development team integrates agent-browser into CI/CD to run end-to-end tests on a single-page application. They use ref-based clicks, waits for network idle, and snapshot diffs to verify UI updates without a visual browser.
A recruitment agency monitors job boards by scheduling periodic automated scrapes with agent-browser. They extract job titles, companies, and links using JSON snapshot parsing.
Offer agent-browser as a hosted browser automation service for enterprises. Customers pay per automation session or per thousand interactions, covering infrastructure and maintenance.
Use agent-browser to extract structured data from public websites and sell cleaned datasets to businesses in need of market intelligence, lead lists, or price comparisons.
Integrate agent-browser into existing SaaS platforms (e.g., CRM, marketing tools) as a native automation feature. Charge a premium for automated workflows over standard manual input.
💬 Integration Tip
Set up isolated sessions via `--session` flag for multi-context testing and use `state save/load` to persist auth state, dramatically reducing repetitive login steps.
Scored May 12, 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
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.
Browser automation CLI (browser-act) for AI agents. MUST trigger when: (1) user mentions 'browser-act' in any form, or user needs to: (2) open/visit/browse/c...