Welcome to Skyvern
Skyvern automates browser-based workflows using LLMs and computer vision. It provides a Playwright-compatible SDK that adds AI functionality on top of Playwright, as well as a no-code workflow builder to help both technical and non-technical users automate manual workflows on any website, replacing brittle or unreliable automation solutions.Why Skyvern?
Traditional approaches to browser automations required writing custom scripts for websites, often relying on DOM parsing and XPath-based interactions which would break whenever the website layouts changed. Instead of only relying on code-defined XPath interactions, Skyvern relies on Vision LLMs to learn and interact with the websites. This approach has a few advantages:Works on unseen websites
Skyvern can operate on websites it’s never seen before, as it’s able to map visual elements to actions necessary to complete a workflow, without any customized code
Resistant to layout changes
No pre-determined XPaths or other selectors that break when websites change
One workflow, many sites
Take a single workflow and apply it to a large number of websites
AI reasoning
LLMs reason through complex situations like inferring information from context
Real-world Use Cases
Skyvern is being used in production to automate workflows across industries:Invoice Downloading
Automatically download invoices from multiple vendor portals with different layouts
Job Applications
Automate the job application process on sites like Lever, Greenhouse, and others
Insurance Quotes
Retrieve insurance quotes from providers like Geico, Progressive, and more - even in different languages
Materials Procurement
Automate materials procurement for manufacturing companies
Government Forms
Navigate government websites to register accounts or fill out forms
Contact Forms
Fill out contact us forms across different websites
How it Works
Skyvern was inspired by the Task-Driven autonomous agent design popularized by BabyAGI and AutoGPT — with one major bonus: we give Skyvern the ability to interact with websites using browser automation libraries like Playwright. Skyvern uses a swarm of agents to comprehend a website, and plan and execute its actions.Performance
Skyvern has SOTA performance on the WebBench benchmark with a 64.4% accuracy. The technical report + evaluation can be found here. Skyvern is the best performing agent on WRITE tasks (eg filling out forms, logging in, downloading files, etc), which is primarily used for RPA (Robotic Process Automation) adjacent tasks.Get Started
Quickstart
Run your first task in 5 minutes
Core Concepts
Learn the building blocks of Skyvern
Features
Tasks
Tasks
Tasks are the fundamental building block inside Skyvern. Each task is a single request to Skyvern, instructing it to navigate through a website and accomplish a specific goal.
Workflows
Workflows
Workflows are a way to chain multiple tasks together to form a cohesive unit of work. Supported features include Browser Tasks, Actions, Data Extraction, Validation, For Loops, File parsing, Sending emails, HTTP Requests, Custom Code Blocks, and more.
Livestreaming
Livestreaming
Livestream the viewport of the browser to your local machine so you can see exactly what Skyvern is doing and intervene when necessary.
Form Filling
Form Filling
Natively capable of filling out form inputs on websites with intelligent context understanding.
Data Extraction
Data Extraction
Extract structured data from websites with custom schemas in JSON format.
File Downloading
File Downloading
Download files from websites automatically. All downloaded files are uploaded to block storage (if configured).
Authentication
Authentication
Supports multiple authentication methods including 2FA (TOTP), password managers (Bitwarden, 1Password), and custom credential services.
Supported LLMs
Skyvern supports a wide range of LLM providers:- OpenAI: GPT-5, GPT-5.2, GPT-4.1, o3, o4-mini
- Anthropic: Claude 4 (Sonnet, Opus), Claude 4.5 (Haiku, Sonnet, Opus)
- Azure OpenAI: Any GPT models
- AWS Bedrock: Claude 3.5, Claude 3.7, Claude 4 (Sonnet, Opus), Claude 4.5 (Sonnet, Opus)
- Gemini: Gemini 3 Pro/Flash, Gemini 2.5 Pro/Flash
- Ollama: Run any locally hosted model
- OpenRouter: Access models through OpenRouter
- OpenAI-compatible: Any custom API endpoint that follows OpenAI’s API format