#106 · Primary category: AI Agents & Automation

skyvern

ai api automation browser browser-automation computer gpt llm playwright powerautomate puppeteer python rpa selenium vision workflow

Automate browser based workflows with AI

Project last updated:08/29/26

GitHub Stars

22.9K

Forks

2.1K

Contributors

95

License

AGPL-3.0

Why we included this project

Maintaining browser automation scripts is a familiar pain: a site tweaks its CSS and your carefully written XPath selectors stop matching. Skyvern takes a different route by using vision-capable LLMs to look at the page the way a human would, then deciding what to click, fill, or extract on the fly. That means the same workflow keeps working across sites and survives redesigns without you rewriting selectors. It comes as a Playwright-compatible SDK, so you can add natural-language commands like page.act and page.extract to the Playwright API you already know, plus a no-code workflow builder for teammates who don't write code. If you're automating form fills, logins, or multi-step tasks on sites you don't control, this is a practical alternative to fragile scripted automation, and the local quickstart makes it easy to try before committing to the hosted cloud.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category