automation▌

Vision-driven desktop automation for native apps using natural language commands and screenshots. \n \n Controls macOS, Windows, and Linux desktops entirely from visual input; no DOM or accessibility labels required \n Operates synchronously with a screenshot-analyze-act loop: connect, observe screen state, execute high-level actions via natural language prompts, then disconnect \n Requires a vision-capable AI model (Gemini, Qwen, Doubao, or similar) configured via environment variables; support

$22

Browser automation with page reuse, persistent cookies, and comprehensive interaction commands. \n \n Supports navigation, clicking, form filling, screenshots, content extraction, element waiting, and JavaScript execution \n Reuses existing pages by default and maintains login state through persistent user data directories \n Includes 20+ functions covering page operations, interactions, waiting, data retrieval, and advanced actions like file uploads and keyboard input \n Accepts CSS selectors a

Automate application deployment across Docker, Kubernetes, AWS, and Vercel with CI/CD pipelines. \n \n Covers Docker containerization with multi-stage builds, GitHub Actions workflows for testing and image building, and Kubernetes deployment with rolling updates and autoscaling \n Includes zero-downtime deployment strategies using blue-green deployments and health check validation \n Provides configuration templates for Vercel/Netlify frontend deployments, environment variable management, and gr

Automate form filling with Playwright MCP, including text input, date/time selection, and file uploads. \n \n Supports multiple form field types: text inputs, date pickers, time selectors, and file uploads \n Navigates to specified URLs and populates forms with provided data without automatic submission \n Includes review checkpoint before form submission to allow manual verification of filled fields \n

<default_to_action> When designing or improving test automation:

ML pipeline automation orchestrates the entire machine learning workflow from data ingestion through model deployment, ensuring reproducibility, scalability, and reliability.

Automate Google Sheets workflows including reading/writing data, managing spreadsheets and tabs, formatting cells, filtering rows, and upserting records through Composio's Google Sheets toolkit.

Automate WhatsApp Business operations through Composio's WhatsApp toolkit via Rube MCP.

Lightweight Gmail integration with standalone OAuth authentication. No MCP server required.