120 related articles
Expert OpinionsDeep dive into real Vibe Coding product experience: tech selection, automation pipelines, prompt engineering, and error handling—revealing the 1000x difficulty gap from cool demo to stable product.
Product ReviewsLightningRAG is an open-source full-stack RAG framework built with Vue and Gin, supporting knowledge base management, vector search, and multi-model integration. A deep dive into its architecture and comparison with LangChain and Dify.
Product ReviewsHands-on test of OpenAI Codex CLI with a visual novel game task, compared against Claude Code and Gemini CLI on planning, code quality, and completion.
TutorialsLearn how to connect OpenAI Codex to DeepSeek V4 Pro and other LLMs using CC Switch and a local API proxy script. Solve API format incompatibility in three easy steps.
Deep DivesCan AI really program? This article explains how LLMs generate code through massive training and pattern matching, and analyzes the true capabilities and limitations of AI coding tools.
Product ReviewsReal-world comparison of Trae Solo vs Cursor building a Python Flask student management system, testing architecture design, code generation speed, runtime results, and practical recommendations.
Expert OpinionsDeep dive into why TypeScript + Zod is the core tech stack for AI full-stack development. Covering type safety, unified full-stack architecture, and AI output validation for enterprise-grade workflows.
TutorialsDeep dive into FastAPI's four core advantages: high-performance async IO, type hints, automatic API docs, and ease of use. Learn the CGI to WSGI to ASGI protocol evolution.
TutorialsA systematic 2025 LLM career transition roadmap covering Python, Transformers, LangChain, LlamaIndex, RAG, Agent development, and fine-tuning across three phases achievable in 2-3 months.
Product ReviewsHands-on review of Alibaba's open-source Qwen Code CLI command-line coding tool, covering installation, API configuration, development experience, and comparison with Claude Code. Powered by a 480B parameter MoE model.
Tech FrontiersAnthropic releases Claude Haiku 4.5, a distilled version of Sonnet 4.5 with near-flagship coding performance, double the speed, and one-third the cost. Scores 73.3 on SWE-Bench, ideal for developers seeking cost-efficiency.
TutorialsStep-by-step tutorial on building an AI photography website with Replit Agent—no coding needed. Covers requirements, API setup, iteration, and one-click deployment for rapid MVP validation.
TutorialsLearn how to use LangChain's ChatPromptTemplate for multimodal image recognition with URL, Base64, and local path inputs, plus PySide6 desktop app integration.
Deep DivesDeep dive into Tencent's open-source LLM knowledge platform WeKnora, covering RAG, autonomous reasoning Agent, and self-maintaining Wiki capabilities, plus its Go-based architecture and enterprise use cases.
TutorialsLearn how to build an AI Agent on Dify with zero code, covering Function Call vs ReAct modes, Exa search tool setup, time-awareness solutions, and Agent best practices.
Deep DivesAnthropic's Advisor Strategy lets Sonnet execute tasks while Opus serves as advisor, cutting costs 12% while boosting SWE-Bench by 2.7 points. A new multi-model AI Agent paradigm explained.
Product ReviewsComprehensive comparison of 80+ AI coding agent tools, with SWE-Bench benchmark rankings covering Devin, Cursor, Claude Code, GitHub Copilot and more, plus pricing analysis to help developers choose.
Product ReviewsDeep dive into Skill-Agent, an open-source FastAPI framework integrating 100+ LLM providers, MCP tool protocol, multi-agent collaboration, RAG knowledge base, and sandbox execution for enterprise AI Agent development.
Product ReviewsMicro-Agent is a lightweight AI Agent framework open-sourced by Fudan University, focused on vertical domain applications. It offers streamlined architecture, low learning costs, and high customization flexibility compared to heavyweight frameworks like LangChain.
Product ReviewsTianshu (mineru-tianshu) is an enterprise-grade open-source AI document preprocessing platform supporting PDF/Office to Markdown conversion, MCP protocol AI assistant integration, with a Vue3+FastAPI full-stack architecture for RAG systems and enterprise knowledge bases.