skyvern
Automate browser based workflows with AI
What is skyvern?
Automate browser based workflows with AI
Overview of skyvern
What it is
Skyvern is an open-source tool that automates browser-based workflows using large language models (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. Skyvern can operate on websites it has never seen before by mapping visual elements to actions, and it is resistant to layout changes because it does not rely on pre-determined XPaths or selectors. The project is licensed under AGPL-3.0.
Key features
- Uses LLMs and computer vision to interact with websites without custom scripts - Resistant to website layout changes (no pre-determined XPaths or selectors)
- Can operate on unseen websites and apply a single workflow to many sites - Provides AI-powered page commands:
page.act(),page.extract(),page.validate(),page.prompt() - AI-augmented Playwright actions with natural language prompts (click, fill, select, upload)
- Includes a no-code workflow builder for both technical and non-technical users - Offers SDKs for Python (
pip install skyvern) and TypeScript (npm install @skyvern/client)
Use cases
Automating manual workflows on any website, such as data extraction, form filling, login, file downloads, and complex multi-step tasks. It replaces brittle or unreliable automation solutions that break when website layouts change.
Getting started
Install Skyvern with pip and run the quickstart: bash pip install 'skyvern[all]' skyvern quickstart For a containerized setup with Docker Compose: bash git clone https://github.com/skyvern-ai/skyvern.git && cd skyvern cp .env.example .env # edit .env to add your LLM API key docker compose up -d Then open http://localhost:8080.
License and pricing
Skyvern is open source under the AGPL-3.0 license. Pricing is not stated beyond being open source.
Based on the project's public README and repository metadata.