231 related articles

Tongyi Qianwen Qwen-Image-3.0 image generation model gets a comprehensive upgrade: supporting 4,500-token ultra-long instructions, pixel-level detail rendering, 12-language knowledge understanding, and ancient painting restoration. This article analyzes its three core capabilities.

Hermes Agent is an open-source autonomous AI Agent with long-term memory and self-evolution. Learn its core innovations, how it compares to Open Cloud, and why it hit 121K GitHub stars.
AstrBot: A Deep Dive into the Multi-Pl…
AstrBot is an open-source AI Agent framework supporting WeChat, QQ, Telegram and more, with multi-LLM compatibility and plugin extensibility. Full technical breakdown inside.

Can't code? Learn how to build a WeChat Mini Program financial management system from scratch using AI coding tool Codex — covering tool selection, OCR invoicing, iteration, and publishing.

No coding experience? Learn how to build a WeChat Mini Program using Codex and AI. A complete beginner's guide covering App ID setup, prompt writing, debugging, and publishing.

Vibe Coding is an AI-driven development paradigm that requires no coding skills. Use natural language to guide AI through design, development, and testing. Learn the 4-step workflow using Gemini, Figma Make, and Claude Code.

A complete guide to Claude Code Skills: what they are, how they differ from Plugins, three installation methods, how to write SKILL.md, trigger mechanisms, and top resource recommendations.

A complete guide to building AI agents with DeepSeek R1: private knowledge bases using RAG, basic/advanced agent implementation, and Coze/Dify workflow tutorials.

DeepSeek seeks $7B for custom AI inference chips; Zhipu AI explores ASIC. Deep dive into China's AI compute independence strategy, multimodal generation, agents, and hardware trends.
GitHub Daily · July 19: The Dual Advan…
GitHub Trending July 19: ktransformers tops the list with heterogeneous inference optimization, while jcode, cua, and AstrBot signal a maturing Agent ecosystem.

Worried about getting your Claude account banned in China? This guide breaks down Anthropic's ban logic and compares three safe approaches: third-party subscriptions, official API, and relay services.

Step-by-step Codex tutorial: build a product finder tool and a flashcard mini program from scratch. Learn prompt techniques, requirements breakdown, and 4 monetization paths.

Is one-prompt app generation really that powerful? We break down three tiers of AI dev tools, expose the gap between demo and production, and compare top domestic platforms including Baidu Miaoda and Ant Lingguan.

Android Remote Control MCP v1.9.0 adds ChatGPT support, OAuth 2.1 auth, and major WebView reliability fixes. Let AI Agents operate any phone app like a human.

Vibe Coding is reshaping software development — use natural language to direct AI through code, design, testing, and marketing. A guide for solo founders and indie developers.

From Claude Chat to CoWork to Claude Code: a complete guide covering the three usage levels, Projects/Skills setup, MCP/CLI tool integration, and real automation workflows like fully automated knowledge video pipelines.

Claude Code is Anthropic's local AI programming assistant that reads your entire codebase, auto-debugs, and delivers far higher accuracy than Cursor and Trae. Here's why it's the strongest AI coding tool today.

Deep dive into the Cocos Creator AI Agent Plugin: three-level context compression, tool approval, multi-agent parallelism, and DeepSeek-powered Mario scene building — all in one test.

Learn how Skill-powered AI Agents can automatically log in to WeChat Official Account backends, scrape data, sort it, and generate Excel reports — eliminating manual analytics work.

An in-depth breakdown of the 7 major attack techniques against AI agents (prompt injection, data poisoning, image attacks, etc.) and a five-layer defense system, with real cases from Doubao and DeepSeek.