Skip to content

skyvernvschromedp

AGPL-3.0 148 17 21,046
250.9 thousand (month) Feb 01 2024 1.0.29(2026-04-02 14:42:44 ago)
12,937 6 172 MIT
May 10 2021 58.1 thousand (month) chromedp(2026-04-01 00:05:30 ago)

Skyvern is an AI-powered browser automation tool that uses large language models (LLMs) and computer vision to interact with websites. Instead of relying on DOM selectors, Skyvern takes screenshots of web pages and uses visual understanding to identify and interact with elements, making it highly resilient to website changes.

Key features include:

  • Vision-based interaction Uses screenshots and computer vision (multimodal LLMs) to understand page layout and identify interactive elements visually, rather than through DOM inspection alone.
  • No selectors needed Describe tasks in natural language and Skyvern figures out what to click, type, and navigate without CSS selectors or XPath.
  • Complex workflow automation Can handle multi-step workflows like form filling, navigation through menus, file uploads, and multi-page processes.
  • Self-correcting When actions fail, Skyvern can analyze the resulting page state and adjust its approach, recovering from errors autonomously.
  • API-first design Provides a REST API for triggering and managing automation tasks programmatically.
  • Open source with cloud option Core engine is open source and can be self-hosted. Also available as a managed cloud service.

Skyvern is particularly effective for automating tasks on websites with complex or dynamic UIs where traditional selector-based automation breaks frequently. It achieved 85.85% accuracy on the WebVoyager benchmark.

ChromeDP is an open-source library for driving browsers using the Chrome DevTools Protocol (CDP) in the Go programming language. It is a high-level library that abstracts away the low-level details of interacting with the CDP and provides a simple, intuitive API for performing common browser automation tasks such as clicking elements, filling out forms, and taking screenshots.

ChromeDP also supports parallel execution of browser tasks, making it well-suited for large-scale web scraping and testing applications. It is considered as one of the most popular Go package for automation and scraping tasks.

Highlights


ai-powerednatural-languageanti-detect

Example Use


```python import requests # Skyvern runs as a service - interact via REST API SKYVERN_API = "http://localhost:8000/api/v1" # Create a task with natural language instructions task = requests.post( f"{SKYVERN_API}/tasks", json={ "url": "https://example.com/contact", "navigation_goal": "Fill out the contact form with test data and submit it", "data_extraction_goal": "Extract the confirmation message after submission", "navigation_payload": { "name": "John Doe", "email": "john@example.com", "message": "Hello, this is a test message", }, }, ).json() task_id = task["task_id"] # Check task status result = requests.get(f"{SKYVERN_API}/tasks/{task_id}").json() print(result["status"]) # "completed" print(result["extracted_information"]) # confirmation message ```
```go package main import ( "context" "fmt" "github.com/chromedp/chromedp" ) func main() { var title, firstParagraph string // create context ctx, cancel := chromedp.NewContext(context.Background()) defer cancel() // run task list (a scraping scenario) err := chromedp.Run(ctx, // go to page chromedp.Navigate("https://www.example.com"), // wait for element to load chromedp.WaitVisible("body"), // extract text from an element (css selector) chromedp.Text("title", &title), // extract first paragraph element chromedp.First(chromedp.ByTagName("p"), &firstParagraph), ) if err != nil { fmt.Println("error:", err) return } fmt.Printf("Title: %s\n", title) fmt.Printf("First paragraph: %s\n", firstParagraph) } ```

Alternatives / Similar


Was this page helpful?