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.

Playwright theatre masks beside a white play button on a blue background

Guides

Playwright works locally but fails in production

The same spec passes on your laptop and fails on the runner. Five reproduced failures show which differences to check and how to fix them.

Oct 25, 2026 · 12 min read

Illustration of a cloud-shaped character holding an MCP sign beside a server rack inside a purple cloud, framed by a browser window

Guides

What is an MCP server? A practical guide for 2026

Most explainers list the benefits. Almost none tell you what a server costs you per step, or how to decide whether you need one. This one does both, using the protocol's own spec and its biggest maintainers' own words.

Oct 25, 2026 · 13 min read

Selenium MCP setup for existing Grid, and when Playwright MCP is the better default

Guides

Selenium MCP: setup and when to use Playwright MCP instead

Keep useful Selenium suites, then inspect what the MCP adapter actually exposes. Grid connections, test runners, waits, and session state remain separate integration decisions.

Oct 24, 2026 · 8 min read

Claude Code browser testing workflow for a local mobile layout bug

Guides

Claude Code browser testing: a practical workflow

One local Claude Code and ego-browser case, with before and after screenshots, a server-side receipt, an injected failure, and clear limits.

Oct 24, 2026 · 8 min read

Illustrated n8n workflow nodes connected to a browser icon above the title Browser Automation for n8n

Guides

Browser automation for n8n: nodes, Browserless, and more

A real n8n 2.40.7 workflow drove a browser, parsed its JSON, wrote a record, and verified it. See the failed readback and Execute Command limit alongside connection options.

Oct 24, 2026 · 16 min read

A local model terminal beside a visible Chromium browser window that an agent drives

Guides

Browser agent with local Ollama models: setup and limits

A local model can drive a real browser, but only when tool calling, context length, and memory line up. This guide wires Ollama to Playwright MCP, Browser Use, and the ego(lite) ego-browser skill, then shows where local agents fail first.

Oct 23, 2026 · 14 min read

Illustrated robot at a signpost marked login, navigate, click, and complete, beside a second figure holding a map and a loading browser window

Guides

How to handle selectors breaking in browser automation

Most broken selectors are not selector problems. Read the error class first, classify the failure against the assumption that broke, and only then decide whether a locator fix, a workflow change, or a supervised agent run is the honest answer.

Oct 23, 2026 · 25 min read

A laptop running a local model beside a visible Chromium browser controlled by an agent

Guides

Browser Use with local LLMs: what actually works

Browser Use documents a local Ollama path, but local tool calling has a narrow margin. Here is the documented setup, the failure modes, and how to tell whether a run actually worked.

Oct 22, 2026 · 18 min read

Orange mascot holding a red cross beside a black and white mascot holding a green check on a blue background

Guides

Why Your Scraper Gets Blocked: Proxy & Fingerprint

A 403, a login redirect and an empty JavaScript page need different fixes. Start with the evidence before changing your proxy or browser.

Oct 20, 2026 · 12 min read