OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Browser Agents

Skyvern

Skyvern is an open-source Python project for automating browser-based workflows with large language models and computer vision. It provides a Playwright-compatible SDK and a no-code workflow builder, alongside a UI and server for running tasks.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Skyvern — OpenViST project profile in Browser Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Skyvern when a recurring workflow spans browser pages and you want to combine conventional browser control with language-model and vision-guided interaction. Its local setup also suits developers who want to run the UI and server themselves.

Who it is for

  • Developers who want to add AI-guided interactions to Playwright browser automation.
  • Technical and non-technical users who want to build repeatable browser workflows.
  • Teams seeking to reduce reliance on site-specific XPath or DOM-based interaction scripts.

Documented uses

  • Automate manual browser tasks across websites.
  • Combine standard Playwright actions with AI-guided page interactions.
  • Build workflows through a no-code interface.
  • Use visual page interpretation to plan browser actions without relying only on predefined selectors.
Before you choose

Requirements & limits

The documented local setup requires Python 3.11, 3.12 or 3.13 for the pip route, or Docker Desktop for Docker Compose. Docker Compose setup calls for an LLM provider API key. Skyvern Cloud requires creating an account.

  • Choose pip for a Python-managed local setup; its quickstart defaults to SQLite.
  • Choose Docker Compose for a containerized setup with the API, UI and bundled Postgres service.
  • The SDK can mix traditional Playwright actions and AI-guided actions, rather than replacing all browser control.
  • The repository is public and licensed under AGPL-3.0.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up Skyvern locally with pip

Install Skyvern and start its local UI and server using the documented Python quickstart.

Before you start

  • Python 3.11, 3.12 or 3.13
  • For Windows, Rust, VS Code with C++ development tools and the Windows SDK

Steps

  1. Install the package with the command below.

    Documented command
    pip install "skyvern[all]"

  2. Run skyvern quickstart.

  3. Open the local UI at http://localhost:8080.

Expected outcome

A local Skyvern setup using SQLite by default, with the UI available to run tasks.

Guide limitations

  • The guide covers local installation and startup, not the configuration or execution of a particular workflow.
  • Postgres can be used instead, but requires starting a local Postgres container or providing a database connection.
Documentation 1 ↗
Source-based practical guide

Start Skyvern with Docker Compose

Start the containerized API, UI and Postgres setup and open its local interface.

Before you start

  • Docker Desktop
  • An LLM provider API key

Steps

  1. Clone the Skyvern repository and change into its directory.

  2. Create .env from .env.example if needed, then add an LLM provider API key to .env.

  3. Run the command below.

    Documented command
    docker compose up -d

  4. Open http://localhost:8080.

Expected outcome

The documented containerized setup starts with its UI, API and bundled Postgres service.

Guide limitations

  • This recipe documents startup only; it does not configure or run a specific browser workflow.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
2 October 2026
Original website title
Skyvern-AI/skyvern · Official homepage title · retained in its source language
How we review sourcesSuggest a correction