Logo
Deploy Now

Stars

22,828

Forks

2,141

Watchers

102

Developer links

Skyvern

Scoring 64.4 on the WebBench benchmark — state-of-the-art among browser automation platforms — Skyvern replaces brittle XPath-based scripts with Vision LLM reasoning that adapts when websites change their layouts. The platform extends Playwright with AI-powered page methods including page.act(), page.extract(), and page.validate() that accept natural language prompts while still supporting traditional CSS selectors as fallback. The drag-and-drop Workflow Studio offers 17+ block types including navigation, extraction, login, loops, conditionals, code blocks, file download, and file upload — enabling non-technical users to build complex multi-step automations without writing code. Self-hosted deployments support bring-your-own-LLM with OpenAI, Anthropic, Gemini, and Ollama, while the multi-engine architecture allows swapping between Skyvern 2.0, OpenAI CUA, Anthropic CUA, or UI-TARS per task with a single parameter. Built-in infrastructure handles persistent browser sessions preserving cookies and localStorage across runs, automatic CAPTCHA solving for reCAPTCHA and hCaptcha, anti-bot bypass for Cloudflare and DataDome, residential proxy rotation across 20+ countries, and a credential vault integrating with Bitwarden and 1Password for secure 2FA management. Real-time session livestreaming via WebRTC enables visual debugging, while step-by-step action logs with screenshots and full LLM diagnostic traces provide production observability. The MCP server integration exposes Skyvern as a tool for Claude, Cursor, Windsurf, and any MCP-compatible AI agent. Connect to 6,000+ apps through Zapier, Make.com, or self-hosted N8N workflows. Deploy via Docker Compose or pip install with a two-command setup. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

Skyvern
Skyvern
Skyvern
Skyvern
Skyvern

Benefits

  • AI-Resilient Web Automation
  • Computer vision and LLM reasoning adapt automatically when websites change layouts, eliminating brittle selectors and reducing maintenance to zero for ongoing automations.
  • No-Code Visual Workflow Builder
  • Drag-and-drop Workflow Studio with 17+ block types chains navigation, extraction, login, loops, and code blocks into repeatable automations without writing any code.
  • Multi-Engine LLM Architecture
  • Swap between Skyvern 2.0, OpenAI CUA, Anthropic CUA, or UI-TARS per task with a single parameter change, optimizing cost and accuracy for each specific workflow.
  • Production Anti-Bot Infrastructure
  • Built-in CAPTCHA solving for reCAPTCHA and hCaptcha, anti-bot bypass for Cloudflare and DataDome, residential proxy rotation across 20+ countries, and persistent session state.

Features

  • Playwright AI Extension
  • Python and TypeScript SDKs add page.act(), page.extract(), and page.validate() natural language methods directly on Playwright page objects with full async support.
  • Credential Vault
  • Securely stores passwords, 2FA TOTP codes, and credit cards with integrations for Bitwarden, 1Password, and Azure Vault without exposing credentials to the LLM.
  • Session Livestreaming
  • WebRTC real-time browser streaming, recorded session playback, step-by-step action logs with screenshots, and full LLM diagnostic traces for production debugging.
  • MCP Server Integration
  • Exposes browser automation as tools accessible to Claude, Cursor, Windsurf, and any Model Context Protocol-compatible AI agent for autonomous web interaction.
  • Code Caching Engine
  • Generated Playwright code is cached after initial LLM generation, making repeat runs 3-5x faster and up to 70% cheaper by skipping the model entirely.