skyvern
Automate browser based workflows with AI
Automating browser workflows with vision-based agents you can self-host.
Your target sites break vision-based automation and need API integrations instead.
About 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.
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.
skyvern is an open-source project written primarily in Python, with 22k stars on GitHub. It was last updated in July 2026.
pip install "skyvern[all]"skyvern vs. the alternatives
All browser & computer use →| Agent | Stars | Pricing | ||
|---|---|---|---|---|
| skyvern | 22k | Python | AGPL-3.0 | Open source |
| UI-TARS-desktop | 38k | TypeScript | Apache-2.0 | Open source |
| page-agent | 22k | TypeScript | MIT | Open source |
| midscene | 14k | TypeScript | MIT | Open source |
| nanobrowser | 13k | TypeScript | Apache-2.0 | Open source |
| Agent-S | 12k | Python | Apache-2.0 | Open source |
