ego (lite) is just a browser, ego is your personal agent across devices.
Join waitlist
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.

Codex CLI in Docker beside a Playwright browser reachable over a bound portGuides

Set Up a Remote Browser Workspace with Codex and Docker

Codex Remote is a phone talking to your Mac. Docker Sandboxes run Codex in a sandbox. Playwright Docker is the browser you can view over noVNC. Assemble them on purpose.

Sep 21, 2026 · 11 min read
Illustrated browser Spaces for agent-browser, Chrome DevTools MCP, and ego (lite) above a mountain landscapeGuides

Browser Automation That Survives UI Changes

Durable browser automation needs more than stable selectors. The right choice depends on whether the workflow is a maintained regression path or changing live work.

Sep 14, 2026 · 13 min readLast updated Sep 21, 2026
Pixel-art ego agent placing a browser window into a cloud box while other browser windows stay connectedGuides

Persistent Browser Sessions Across Agent Runs

A session that survives one run and dies on the next is the most common agent failure that looks like an application bug. Here is the full lifecycle: how to establish, preserve, verify, isolate, expire, and recover a browser session, with the profile-lock and session-cookie traps named.

Sep 11, 2026 · 11 min readLast updated Sep 21, 2026
How AI agents connect to your existing browser and logged-in sessionsGuides

How to connect AI agents to your existing browser

The most-requested agent capability across forums and issue trackers, mapped honestly: four routes with their mechanisms and risks, the combined solution they point to, and the two questions that pick yours.

Aug 15, 2026 · 10 min readLast updated Sep 21, 2026
AI scraping behind login walls: digging past padlocks and login screensGuides

AI Scraping Behind Login Walls: X and LinkedIn (2026)

Scraping behind a login is three routes, not one: inject a session, reuse a real browser's session, or point a no-code tool at it. For X and LinkedIn, collect only what the signed-in account is allowed to read, record evidence, and never treat a login as permission to bypass controls.

Aug 07, 2026 · 10 min readLast updated Sep 21, 2026
Illustration of a cloud-shaped character holding an MCP sign beside a server rack inside a purple cloud, framed by a browser windowGuides

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.

Sep 20, 2026 · 13 min read
Agent harness: what it is, how to build one, how to chooseGuides

Agent harness: what it is, how to build one, how to choose

Agent equals model plus harness. Three authorities currently disagree about where a harness ends and a runtime begins, so this starts by settling that, then builds one in forty lines, then looks at the part almost nobody writes about: what the agent actually sees on the web.

Sep 20, 2026 · 18 min read
Context engineering for browser agents: what an observation costsGuides

Context engineering for browser agents: what an observation costs

Almost every article on this term uses text-only examples. Across the top 24 results, 19 fetchable pages and 64,225 words, "accessibility tree", "screenshot" and "browser automation" each appear zero times. That is the gap this fills.

Sep 20, 2026 · 12 min read
A local model terminal beside a visible Chromium browser window that an agent drivesGuides

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.

Sep 19, 2026 · 14 min read