Skyvern

Open source browser automation agent using LLMs and vision

By Nathan KesslerUpdated Jul 27, 2026

Each tool is evaluated against our methodology using public docs, vendor demos, and hands-on testing.

Some links on this page are affiliate links. We earn a commission if you sign up – at no additional cost to you. Our editorial assessment is independent and never paid. How we review.

What is Skyvern?

Skyvern is an AI-powered browser automation platform from Y Combinator's S23 batch. It replaces CSS selectors with LLM reasoning plus computer vision, so automations keep working through UI changes. It also handles login flows with 2FA/TOTP, CAPTCHA solving, document downloads, form filling, and data extraction. Workflows can be built through natural-language chat, SOP or document upload, browser recording, a visual workflow builder, or Python/TypeScript SDKs, with support for bringing your own LLM (OpenAI, Anthropic, Gemini, or local via Ollama).

Our verdict

The core engine is open source (AGPL-3.0, 22.6k GitHub stars) and can be self-hosted via Docker, but anti-bot measures are reserved for the managed cloud tier. Self-hosted deployments lose the CAPTCHA-solving and stealth handling that make the vision-based approach resilient to blocking. It fits teams that want an LLM-driven alternative to selector-based automation for workflows that break on UI changes, less so anyone needing production anti-bot evasion without paying for the cloud product.

Categories:

Agentic Automation

Agentic automation tools give an LLM control of a browser to navigate, click, and fill forms toward a goal, rather than following a fixed script. They are newer and less predictable than selector-based scraping, but they handle sites and workflows that are hard to hardcode.

Tags:#freemium #open-source #self-hosted #js-rendering #structured-output #captcha-solving #python-sdk #javascript-sdk #vision-model #ai-agents #browser-automation

Similar tools

See Agentic Automation

Stagehand

Open source AI browser automation SDK from Browserbase

FreemiumJul 2026Agentic Automation

Browser Use

Open-source browser agent framework plus a paid cloud API

FreemiumJul 2026Agentic Automation

CloudCruise

API platform for browser automation agents in healthcare workflows

FreemiumJul 2026Agentic Automation

How Skyvern compares

Stagehand

Stagehand is an open-source browser automation framework that also pairs LLM reasoning with browser control, an alternative to selector-based scripting.

Browser Use

Browser Use is an open-source AI agent framework for browser automation, competing directly with Skyvern's approach of using LLMs in place of hardcoded selectors.

CloudCruise

CloudCruise is a managed browser-agent automation platform, comparable to Skyvern's cloud offering for teams that prefer not to self-host.

Comparisons

Skyvern alternatives

Visit

Skyvern

Visit