agent-browser-clawdbot-bakHeadless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection
Install via ClawdBot CLI:
clawdbot install chenjinsong/agent-browser-clawdbot-bakGrade 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 17, 2026 · audit v1.0
Generated Sep 22, 2026
Run multi-step DOM interaction tests on complex React SPAs using accessibility tree snapshots and ref-based element selection. Tests cover authentication flows, CRUD operations, and role-based UI states with deterministic selectors. Integrate into CI pipelines to catch regressions before deployment.
Schedule daily browser sessions to open e-commerce sites, search product catalogs, and extract pricing, stock, and promotional data. Use network mocking to simulate requests and state persistence to bypass login walls. Store extracted data in a central analytics warehouse for trend analysis.
Simultaneously test admin and standard user workflows in isolated browser sessions with separate auth states. Validate permission boundaries, data visibility, and cross-session interactions without manual setup. Reuse saved cookie/storage state to skip lengthy login sequences.
Automate browsing of directory and social sites to extract contact details, company info, and LinkedIn URLs. Use wait conditions like networkidle and text-based waits to handle dynamic content. Feed structured JSON output into CRM systems for outbound sales campaigns.
Automate repetitive form filling and document uploads on legacy portals that lack APIs. Use scoped snapshots and ref-based interactions to handle iframes and complex validation. Persist authentication state to avoid logging in for each submission batch.
Offer outsourced end-to-end test automation for SaaS companies using agent-browser. Build reusable test suites that run on every commit, reducing manual QA costs and flakiness.
Sell subscription access to dashboards and APIs that aggregate scraped web data (pricing, leads, trends). Use agent-browser for reliable, high-volume extraction behind the scenes.
Provide expert guidance, custom script development, and workshops for teams adopting agent-browser. Help clients migrate from flaky Selenium/Puppeteer setups to deterministic ref-based automation.
💬 Integration Tip
Install agent-browser globally via npm, then wrap commands in scripts to parse JSON snapshot refs. Always call snapshot -i --json after navigation or page changes before interacting with refs.
Scored Apr 28, 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...