#JSON-RPC
294 related articles
·7 min
Agent Loop Explained: The Core Runtime Mechanism and Think-Act Cycle of AI Agents
Deep dive into Agent Loop mechanics: the think-act cycle, how agents differ from LLMs, termination conditions, and design principles for building autonomous AI Agent systems.
Read more →
·8 min
MCP Server or Agent Skills? A Clear Guide to Architecture Decision-Making
MCP Server vs Agent Skills: how to choose? This article systematically outlines an AI Agent architecture decision framework across three dimensions—essential differences, applicable scenarios, and judgment criteria.
Read more →
·7 min
Cloudflare Natively Supports the x402 Protocol: How Micropayments Are Reshaping Web Monetization
Cloudflare announces native x402 HTTP payment protocol support, enabling developers to charge stablecoin micropayments for API calls without accounts or keys. Deep dive into how x402 works and its impact on AI Agent economics.
Read more →
·7 min
Linked Context: How AI Agent Skills Can Point to the Entire Open Web
Deep dive into Skill Studio's "Linked Context" mechanism—skill files become real-time URL fetches instead of pre-loaded copies, extending AI Agent progressive disclosure to the entire open web.
Read more →
·3 min
Codex APP Deep Dive: Comparison with Claude Code and How to Choose
In-depth comparison of Codex APP vs. Claude Code and Cursor: pricing, stability, and capability differences. Discover Codex's unique strengths in frontend UI development and how to choose the right AI coding tool.
Read more →
·4 min
Complete Beginner's Guide to Claude Code in 19 Minutes
A complete beginner's guide to Claude Code covering setup, Plan Mode, CLAUDE.md project memory, MCP connectors, Skills, Plugins, and deploying via GitHub and Vercel.
Read more →
·3 min
How MCP Enables AI Agents to Automatically Follow Design Systems
How MCP connects design systems with AI Agents for real-time spec queries and automatic compliance. Covers context engineering, MCP architecture, and AI-driven development.
Read more →
·3 min
Dify + MCP in Practice: Build a Multi-Function AI Agent Workflow in Four Steps
Learn how to build a multi-function AI agent workflow using ModelScope MCP Plaza and Dify, featuring dietary recommendations, algorithm practice, news, and travel planning with zero coding.
Read more →
·4 min
AI Keeps Failing at Writing Code? You Need Knowledge Bases, Skills, MCP, and Agents — All of Them
AI coding failures in enterprise aren't about weak models — they're about missing frameworks. Learn how Knowledge Bases, Skills, MCP, and Agents work together.
Read more →
·4 min
AI-Driven HFSS Simulation: Codex Automates AEDT Modeling and Solving via MCP
Learn how Codex or Claude Code uses AEDT MCP to connect with Ansys HFSS, automating Wilkinson power divider modeling, solving, and post-processing end-to-end.
Read more →
·3 min
Getting Started with AI Agent Development: Core Concepts, Architecture, and Practical Essentials
A comprehensive guide to AI Agent development covering core concepts, the Perception-Brain-Action architecture, key differences from chatbots, four essential components, and mainstream framework selection.
Read more →
·3 min
Essential for Embedded Development: Three Must-Have MCP Servers
Three essential MCP servers for embedded development: Debugger MCP, VS Code MCP Server, and Zephyr Official MCP — solving AI coding pain points like missing syntax checking and documentation access.
Read more →
·3 min
Playwright vs Selenium In-Depth Comparison: A Test Automation Tool Selection Guide for the AI Era
In-depth comparison of Playwright vs Selenium covering DevTools Protocol, async performance, smart locators, and AI MCP integration to help you choose the best automation testing tool.
Read more →
·2 min
sakana-mcp: Driving AI Scientist Autonomous Research Cycles via MCP Protocol
sakana-mcp wraps Sakana AI Scientist v2 as an MCP server, letting Claude and Cursor act as research directors to orchestrate autonomous research cycles.
Read more →
·3 min
Codex Hands-On from Scratch: Building a Full-Stack World Cup App Without Writing Code
Learn how to build a full-stack World Cup app with OpenAI Codex without writing code, covering multi-session concurrency, MCP voice synthesis, Skill encapsulation, and scheduled task automation.
Read more →
·3 min
DeepSeek V4 Flash Free Usage Guide: Configuration for Cherry Studio and CC Switch
DeepSeek V4 Flash is free for a limited time with zero token charges. Learn how to register on OpenModel and configure it in Cherry Studio and CC Switch.
Read more →
·3 min
Codex Record & Replay Plugin: Record Once, Auto-Generate Reusable Skills
Explore OpenAI Codex's Record & Replay plugin that captures mouse and keyboard actions via MCP server to auto-generate reusable, shareable Skills for zero-code RPA automation.
Read more →
·3 min
MCP vs Skills: Understanding the Key to AI Testing Efficiency
Understand the key differences between MCP (Model Context Protocol) and Skills through practical analogies and real testing scenarios to boost AI-driven test automation efficiency.
Read more →
·2 min
The Essential Difference Between Skill and MCP: A Kitchen Analogy That Makes It Crystal Clear
Skill and MCP are two easily confused core concepts in AI Agent development. This article uses a kitchen analogy to explain how Skill (recipe/methodology) and MCP (kitchen assistant/tool connection) differ and work together.
Read more →
·3 min
Claude Code Skills and MCP Resources: A Complete Guide from Beginner to Expert
A comprehensive guide to Claude Code Skills and MCP resources, covering international platforms like Skills.mp and Smithery plus Chinese alternatives, with a quick selection guide to boost AI coding productivity.
Read more →