Skip to content
FindOpenSource

Skyvern

Automates browser-based workflows using computer vision and LLMs to understand and interact with websites, even ones it hasn't seen before.

Overview

Skyvern uses a vision-based approach rather than relying on brittle DOM selectors or site-specific scripts: it looks at a page the way a person would, and can generalize to websites it hasn't been configured for ahead of time. It's positioned as a workflow-automation platform (with a UI for defining and monitoring runs) more than a raw library.

Skyvern is a fit for teams automating browser workflows across many different, changing, or unfamiliar sites where a vision-first approach is more resilient than DOM-based automation like browser-use (also in this catalog). Note it's licensed under AGPL-3.0, a stronger copyleft license than most projects in this catalog.

Categories
AI Agents & Agent Tools
Keywords
computer-usebrowser-automationvision-based-agent
Languages
Python, TypeScript
License
AGPL-3.0

Spotted an error? Suggest an edit on GitHub.