ego(lite) articles
Everything you need to know about browser automation
Guides, insights, comparisons, and reviews across Playwright MCP, Browser Use, Chrome DevTools MCP, coding agents, and the browsers they drive.
Comparisons
Deterministic browser automation vs AI agent clicking
A fixed script and a runtime agent can share browser tools. Define the action-selection boundary and verify the same output before judging either route.
Oct 15, 2026 · 9 min read
Guides
Playwright MCP for Codex: setup and verified browser calls
Follow registration through to a fresh result check. Separate native Codex tools from shell wrappers and preserve the actual browser execution path.
Oct 15, 2026 · 9 min read
Comparisons
Playwright MCP vs Browser Use: which does your agent need
The most common mistake in this comparison is treating the two as rivals in one category. One is a protocol tool your coding agent drives step by step; the other is an autonomous framework with its own loop. Pick by task shape.
Oct 15, 2026 · 9 min read
Guides
Claude Code browser login: how to automate sites behind auth
The agent's browser isn't signed in to anything; that's the whole problem. Three real routes with steps and risk profiles, plus practical guidance for CAPTCHAs, OAuth loops, session expiry, 2FA, and scheduled runs.
Oct 15, 2026 · 9 min read
Comparisons
Playwright vs Puppeteer for web scraping: 2026 verdict
The speed debate is mostly settled and mostly irrelevant: API design, stealth ecosystems, and browser coverage decide real scraping outcomes. Median benchmark numbers, practitioner reports, and a verdict by scenario.
Oct 15, 2026 · 17 min read
Comparisons
Headless browser vs real browser for AI agents
Login-walled work may need an authorized real browser; batch, stateless work usually wants headless. See why long-running agents need persistent computers, then map headed vs real and headless tools to tasks.
Oct 15, 2026 · 28 min read
Reviews & roundups
Best AI browsers and browser automation tools in 2026
AI-native browsers, browser engines, and external automation tools solve different jobs. Compare the category first, then pick among eleven options for scraping, testing, and daily work.
Oct 15, 2026 · 18 min read
Reviews & roundups
Best MCP for browser automation: the 2026 shortlist
Five browser MCP servers scored on the four things that decide an agent workload, and the honest conclusion: the best token-and-login outcome often isn't an MCP at all.
Oct 15, 2026 · 10 min read
Insights
Playwright MCP token problem: why snapshots eat your context
High MCP token usage isn't a settings problem, it's the architecture: every action returns the page's accessibility tree into your context. We trace where the tokens go and rank the three escape routes.
Oct 15, 2026 · 9 min read