agent-browser-clawdbot-disabled-20260401-112736Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection
Install via ClawdBot CLI:
clawdbot install tmundi3210/agent-browser-clawdbot-disabled-20260401-112736Grade 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 19, 2026
An AI agent navigates an e-commerce admin panel to process orders, check inventory, and update shipping status. The agent uses ref-based selection for reliable interactions across complex SPAs, reducing manual effort.
A QA agent uses session isolation to simultaneously test two different user roles in a web app (e.g., admin and regular user). It validates workflows without interfering between sessions, ensuring consistent behavior.
An agent logs into a data-rich portal, saves auth state, and then scrapes structured data from multiple pages. It reuses saved state across runs to skip repetitive login steps, maximizing efficiency.
An AI agent performs bulk data entry into a CRM system by navigating tabs, filling fields via refs, and submitting forms. It waits for network idle to ensure data persistence, lowering error rates.
An agent snapshots accessibility trees of key pages, extracts refs for interactive elements, and checks for missing labels or roles. It generates structured JSON reports for compliance teams.
Offer agent-browser automation APIs to enterprises needing reliable web task automation. Monetize via usage-based pricing (per session/request) and volume discounts.
Provide a platform that integrates agent-browser with AI agents for end-to-end workflow automation. Revenue from per-seat licenses and premium support.
Deliver automated testing services for web applications using agent-browser's session isolation and deterministic selection. Charge per test suite or hourly.
💬 Integration Tip
Wrap agent-browser commands in an AI agent's function-calling loop; always use -i --json for snapshot output to enable deterministic ref-based selection.
Scored Jun 19, 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...