Skyvern: Automate Browser Workflows With LLMs + Vision
Skyvern-AI/skyvernSkyvern automates browser-based workflows using vision LLMs and computer vision instead of hand-written selectors. It reads a page the way a person would, so a form-filling or data-entry flow keeps working when the site's layout shifts and an XPath script would have broken.
Reach for Skyvern if you're automating flows across websites you don't control and you're tired of XPath scripts breaking on every redesign. Skip it if you're automating one stable internal app — a plain Playwright script will be faster and cheaper than sending each step through a vision model.
The problem it solves
Traditional browser automation pins actions to a page's structure: click this XPath, read that DOM node. The moment a site ships a redesign, the selectors miss and the script fails silently. Maintaining a fleet of these scripts across third-party websites is a constant game of whack-a-mole.
What is it?
Skyvern is an open-source (AGPL-3.0) tool that automates browser workflows using LLMs and computer vision. Rather than relying only on code-defined XPath, it uses vision models to look at a page and decide how to interact with it. It offers a Playwright-compatible SDK that layers AI commands on top of Playwright, plus a no-code workflow builder for non-developers.
Why it's getting attention
Browser automation that survives layout changes is a long-standing pain, and pairing vision LLMs with Playwright is a concrete answer to it. The README frames Skyvern as an evolution of task-driven agents like BabyAGI and AutoGPT, but pointed at real browser tasks — with a swarm of agents that read a site, then plan and execute actions.
Key features
- ✓Vision-LLM interaction that reads pages visually instead of relying only on XPath/DOM selectors
- ✓A Playwright-compatible SDK that adds AI commands on top of standard Playwright
- ✓A no-code workflow builder for non-technical users
- ✓A swarm-of-agents approach to comprehend a site, then plan and execute actions
- ✓Runs against arbitrary public websites, not just apps you control
- ✓Local pip setup defaults to a SQLite database, with Postgres and Docker options
Best use cases
- •Filling out forms or applications across websites whose layouts change often
- •Automating repetitive data-entry or lookup tasks on third-party sites
- •Letting non-developers build browser automations without writing selectors
- •Replacing brittle Selenium/Playwright scripts that break on site redesigns
How to install / try
Skyvern needs Python 3.11, 3.12, or 3.13. Install with `pip install skyvern` (the README notes `uv pip install skyvern` if pip hits a litellm/fastmcp resolution error), then run `skyvern quickstart` and `skyvern run server` — these default to a SQLite database at `~/.skyvern/data.db`, so the pip path works without Postgres or Docker. A docker-compose option is also documented.
How to use
You can drive Skyvern through its Playwright-compatible SDK, adding AI commands to a Playwright script, or build flows visually in the no-code workflow builder. Give it a task on a target website and its agents read the page with vision and carry out the steps. See the project docs for the SDK commands and workflow features.
Strengths
- ✓Survives layout changes that break XPath/selector-based automation
- ✓Playwright-compatible, so it fits into existing Playwright workflows
- ✓The pip + SQLite default lets you try it without standing up Postgres or Docker
- ✓A no-code builder opens automation to non-developers, not just engineers
Limitations & risks
- △Every step routes through a vision LLM, so it's slower and costs more than a plain scripted run
- △AGPL-3.0 copyleft can complicate commercial or embedded use
- △The README documents pip dependency-resolution failures (litellm/fastmcp) that push you to uv
- △Vision-driven automation on arbitrary sites is still probabilistic — it can misread a page or take a wrong action
- △You supply LLM API access, so running it at scale means real per-task model spend
Alternatives
Who should try it — and who should skip
Teams automating workflows across websites they don't own, where redesigns keep breaking selector-based scripts. It fits both engineers (via the Playwright-compatible SDK) and non-developers (via the no-code builder). If you're automating one stable internal app, a direct Playwright script will be leaner and cheaper.
Frequently asked questions
Selenium and Playwright act on code-defined selectors like XPath. Skyvern adds vision LLMs that read the page visually, so flows survive layout changes that would break selector-based scripts.
No. Per the README, `skyvern quickstart` and `skyvern run server` default to a SQLite database at ~/.skyvern/data.db, so the pip path runs without Postgres or Docker. Postgres and docker-compose are optional.
Yes. Alongside the Playwright-compatible SDK, it has a no-code workflow builder aimed at non-technical users.
AGPL-3.0. That's a strong copyleft license, which can affect how you use it in commercial or networked products.