browser▌

Fast, persistent browser automation with session continuity across sequential agent commands. \n \n Supports three browser modes: headless Chromium, real Chrome with profile support, and cloud-hosted remote browsers with proxy configuration \n Includes 15+ command categories covering navigation, page inspection, interactions, data extraction, cookie management, and JavaScript execution \n Offers cloud session management, local server tunneling via Cloudflare, and parallel subagent execution thro

Cloud browser automation for pages requiring clicks, forms, login, and pagination. \n \n Supports interactive workflows: click elements, fill forms, navigate multi-step flows, handle pagination and infinite scroll \n Persistent profiles survive session close, enabling login-then-work patterns where authentication state is retained across reconnects \n Core commands include open , snapshot -i (element discovery with @ref IDs), click , fill , type , scrape , scroll , wait , and eval for JavaScript

Grants browser access to another AI agent with scoped permissions and per-agent tab/session isolation.

Imports cookies from a real browser into the headless browser context so authenticated flows can be tested.

Launches a visible AI-controlled browser window with the GStack sidebar and anti-bot behavior for live observation and control.

Headless Chromium-based testing browser for screenshots, interaction, layout checking, form handling, and state verification.

Minimal CDP tools for collaborative site exploration.

Playwright-based browser automation with element refs and session persistence for AI agents. \n \n Provides 6 core functions: open (navigate + configure), snapshot (refresh element refs), interact (click/fill/drag/upload/scroll), screenshot, execute (JavaScript), and close \n Uses @e ref system for element targeting; refs invalidate after navigation and require re-snapshot to refresh \n Supports video recording with optional cursor indicator, proxy routing, file uploads, and drag-and-drop intera

You are a browser automation expert who has debugged thousands of flaky tests and built scrapers that run for years without breaking. You've seen the evolution from Selenium to Puppeteer to Playwright and understand exactly when each tool shines.

Browser automation for cmux webviews with snapshot-based element targeting and state verification. \n \n Open surfaces, navigate, and verify URLs before acting; snapshot with --interactive to get fresh element references for clicks, fills, and selections \n Wait patterns support selectors, text content, URL changes, load states, and custom JavaScript functions with configurable timeouts \n Recommended workflow: navigate → verify URL → wait for load state → snapshot → act → snapshot again to hand