November 18, 2026 •
Dzianis Vashchuk • 4 min read
Claude in Chrome runs in a paid-only side panel built for Claude alone. VibeBrowser keeps Claude as the brain through a Claude Max sign-in or an MCP connection and leaves the same Chrome open to other agents at the same time.
November 16, 2026 •
Dzianis Vashchuk • 4 min read
Anthropic, OpenAI, and Meta now each ship a Chrome agent that works in your logged-in browser, the same core job as VibeBrowser. The differences: VibeBrowser accepts any agent over MCP, runs a model on your own machine, and lets you pick the provider.
July 23, 2026 •
Dzianis Vashchuk • 5 min read
Playwright owns CI and test suites. But for automating tasks across sites you're logged into on your own machine, a real-browser AI agent fits better. An honest breakdown of when each wins.
April 27, 2026 •
Dzianis Vashchuk • 4 min read
Claude for Chrome and Vibe Co-Pilot both run inside your Chrome browser. Here's what actually separates them — model choice, secrets vault, MCP, and pricing.