Browser Automation
Use Selenium with CrewAI
Selenium connects to CrewAI through a built in by the framework vendor path (crewai_tools SeleniumScrapingTool). This page records what that connection looks like and links the evidence behind it.
Pairing facts
Why this pairing
The long-running open-source WebDriver standard for driving real browsers, now adding WebDriver BiDi for event-driven control.
Best for: Cross-browser automation that must run the same flow in Chrome, Firefox, Edge, and Safari Teams with existing Selenium Grid infrastructure Agents whose browser steps need deterministic, scripted control
Not ideal for: Agent-first workflows where the model should plan clicks from page state Serverless or ephemeral environments where managing browsers and drivers is unwanted overhead
Configuration
from crewai_tools import SeleniumScrapingToolSource: https://pypi.org/project/crewai-tools/1.9.3/. Examples use placeholders only.
Evidence
The crewai-tools PyPI page lists SeleniumScrapingTool under Web Scraping in the CrewAI tools collection.
https://pypi.org/project/crewai-tools/1.9.3/
Compatibility here means the cited page documents the pairing. It does not mean AgentsUse benchmarked the combination or that every version works unchanged. Pin versions, run the tool on a small job first, and review the first outputs before widening access.
Watch for
- You own browser and driver lifecycle management, plus Grid operations if you scale out.
- The model is imperative scripting, so agent planning and recovery need a layer you build or adopt.
- Waits, timing, and flaky selectors remain manual work at scale.