56 related articles

Argos is a browser AI agent that automatically performs real tasks like clicking and filling forms within your logged-in accounts. It supports Gmail, Google Docs, GitHub, and more with local data processing.

Deep dive into Kitesurf—a lightweight browser built on V8 Isolates for AI Agents. Learn how its millisecond cold starts, high concurrency, and sandbox isolation solve traditional browser bottlenecks in AI automation.

Learn how to parallelize Cursor browser Workers from serial to parallel execution using distributed Worker pools, proxy pools, token bucket algorithms, and exponential backoff to compress 2000-3000 page scraping tasks from hours to 15-20 minutes.

Deep dive into the verification browser for AI agents: how 13ms verification windows and one-call checks solve hallucination problems in browser automation, enabling the leap from capability to trustworthiness.

A detailed guide to Google's WebMCP standard proposal, covering imperative and declarative tool building, smart home and car configuration demos, and Chrome DevTools debugging for AI agent tools.

A step-by-step Pi Agent configuration tutorial covering installation, LLM connection, extension ecosystem, MCP setup, and Token-saving tips. Learn to build a truly controllable AI coding assistant.

A data-deletion disaster reveals the biggest AI Agent risk: the problem isn't the model, it's Harness design. Learn context management, process standards, and permission isolation.

OpenAI Codex is more than a coding tool—it's an AI agent that writes code, makes slides, and operates browsers. This guide covers its four versions, permission modes, plugins, automation, and six best practices.

Deep dive into AI-era automated testing: using Pytest + Playwright + MCP for stable automation, constraining code conventions with Skills, avoiding non-determinism and high token costs. Includes real debugging war stories.

A complete workflow from Google I/O: use Antigravity, Modern Web Guidance, and Chrome DevTools MCP to build Chrome extensions automatically — from prompt to publish.

A deep dive into the WebMCP proposal: how AI agents read websites, how to expose structured tools via imperative and declarative APIs, and how to audit agentic readiness with Lighthouse.

Google's DevTools for Agents opens Chrome DevTools to AI coding agents, enabling autonomous end-to-end debugging — from reproducing errors to fixing source code — via console logs, network requests, and source maps.

Chrome DevTools for Agents, unveiled at Google I/O, gives AI coding agents a closed feedback loop with Lighthouse audits, user input simulation, and device emulation.

AI agents are revolutionizing JS reverse engineering. This deep dive covers built-in tool chains, automation modes, prompt engineering for e-commerce, and full pipeline automation from parameter extraction to database storage.

In-depth hands-on review of Alibaba's open-source web automation tool PageAgent: three integration methods, script execution analysis, and a full breakdown of current limitations. Add AI Agent capabilities to web pages with one line of JS.

BrowserWing is an open-source browser action recorder (1300+ GitHub stars) with 78 built-in scripts for GitHub, Bilibili, Zhihu, and more. Record once, run repeatedly, and let AI Agents reliably execute fixed web workflows.

Browser Use is an open-source AI Agent framework that lets LLMs autonomously drive browser operations via natural language. This article breaks down its four-layer architecture, core Agent loop, CDP perception layer, dynamic Tools dispatch, and its Skills, Sandbox, and MCP extension capabilities.

GPT-5.6 is officially released, merging ChatGPT and Codex into one app and launching the three-tier Sol, Terra, and Luna models. A detailed breakdown of 16 hands-on tests plus Worker mode and Codex dev upgrades.

Playwright E2E Builder is an AI Skill installed in Cursor that transforms UI automation from throwaway scripts into sustainable engineering assets through a four-step workflow, with built-in locator health checks.

Fortress is an open-source stealth Chromium built for AI Agents. It eliminates automation fingerprints to bypass Cloudflare and other anti-bot systems.