Agents: guides & tutorials

Traditional automation (Playwright or Puppeteer) depends on stable selectors. If a team hardcodes .submit-btn and the site renames classes, the job fails.

browser-use inverts that: you describe the goal in natural language, the library feeds a sanitized view of the page to an LLM, and the model plans clicks, typing, and extractions through Playwright.

This guide covers the architecture, where it breaks in production, and how to pair it with Apify Actors when you need cloud browsers and proxies.

Scrapling is a Python framework that uses structural similarity to keep selectors working when markup changes. OpenClaw is a local daemon that connects messaging channels to autonomous LLM workflows. Used together, you can say “check competitor prices” in chat and have the agent trigger a cloud scraper that handles WAFs and headless rendering.

This tutorial wires those pieces: Scrapling extraction inside an Apify Actor, triggered from an OpenClaw Node skill via the Apify REST API.

Most people use hosted assistants (ChatGPT, Claude, Gemini). That is convenient, but sensitive threads, internal repos, and private DMs pass through someone else’s servers. For engineers and privacy-conscious teams, OpenClaw (successor lineage to projects sometimes referred to as Moltbot / Clawdbot) flips the model: you host the Gateway, you pick the model, and you decide which tools (files, shell, HTTP, browser, custom skills) the agent may use.

As of March 2026, OpenClaw is among the largest open-source AI assistant projects on GitHub (on the order of hundreds of thousands of stars—exact counts move quickly; check the repo for the live number). This guide explains what it is, how to run it, where it breaks down operationally, and how to pair it with Apify when local scraping is too fragile for production sites.

In February 2026, Google unveiled an early technical preview of WebMCP (Web Model Context Protocol), a proposed web standard incubated by the W3C Web Machine Learning Community Group in collaboration with Microsoft. Introduced in Chrome 146 Canary, its architecture proposes a radical shift: rather than forcing AI agents to parse opaque DOM structures via CSS selectors, websites explicitly declare deterministic API endpoints that local agents can execute.

If adopted, WebMCP fundamentally alters the economics of web data extraction. This technical analysis explores how the protocol operates, its architectural failure modes, and what data engineers must build to maintain extraction pipelines through to 2030.