#AI编程
9640 related articles
Zero-Cost Global Deployment with Supabase + Vercel: A Needora Case Study
Learn how to deploy a global product at near-zero cost using Supabase and Vercel, with the Needora MVP as a real-world example. Skip ICP registration and ship fast.
Claude Code Adds Mods and AGENTS.md Support: A Deep Dive
Anthropic adds Mods plugin system and AGENTS.md support to Claude Code, alongside Projects redesign, background computer use, Diff panel, and Skills evaluation tools.
DeepSeek Harness Goes Open Source: An AI Agent Foundation Where Everything Is a Plugin
DeepSeek Harness is now open source. Built on an "everything is a plugin" philosophy, it supports 20+ LLM providers and launches a local Web UI with a single command.
AI Large Language Model Learning Roadmap: From Theoretical Foundations to Agent Development
A complete AI large model learning roadmap: from Transformer theory and PyTorch/Hugging Face frameworks to API calls, fine-tuning, Agents, and LangChain — a clear path from beginner to job-ready.
AI Agent Development: A Complete Beginner's Guide from Concepts to Practice
A complete beginner's guide to AI Agent development: from chatbots to intelligent agents, Stanford Smallville & ChatDev, and a 3-phase LangChain learning path.
Andrew Ng on Agentic AI: How to Build High-Value Agent Applications with Evaluation-Driven Development
Andrew Ng's Agentic AI course opening: cut through the marketing noise, explore real agentic workflow use cases, and learn why evals and error analysis are the key to building high-value AI agents.
Bolt Forge: Open-Source Model-Powered Coding Agent with 50x Usage Boost
Bolt Forge is Bolt.new's open-source coding agent giving Pro users up to 50x usage with no daily caps, reaching 91% of top paid model performance on internal benchmarks.
Ruby UTCP: A Scalable, Secure Alternative for Tool Calling
Ruby UTCP brings UTCP 1.1 to the Ruby ecosystem, supporting 12 transport protocols including HTTP, gRPC, WebSocket, and MCP — a scalable, secure alternative to MCP for AI agents.
LucentraCode: An AI Coding CLI Tool Without Usage Limits
LucentraCode is an AI coding CLI with no usage limits, supporting GPT, Claude, Gemini, Grok and more. Covers debugging, refactoring, testing, and large codebases.
Deep Dive: Claude Code's Effort Levels and Caching Mechanisms
Deep dive into Claude Code's effort levels, prompt caching, and subagent behavior. Learn the truth about Ultracode and Ultrathink, and how cache lifetimes impact cost.
What Is an AI Agent? One Relatable Example That Explains It All
What is an AI Agent? Using a relatable "attend class for me" analogy, this article demystifies Agents: they decompose tasks and call LLMs repeatedly via rules and prompts — no magic involved.
Getting Started with WorkBuddy: Turning AI from a Chatbot into a Productive Desktop Employee
WorkBuddy is a desktop AI agent that operates your local PC to handle file management, docs, and office tasks. Learn how it differs from Codex and how to get started.
WorkBuddy Beginner's Guide: Getting Started with AI Agent Digital Employees from Scratch
WorkBuddy beginner's guide: from installation and three work modes to multimodal image/video generation. Learn how this Chinese AI Agent handles file organization, storybook videos, and more.
Building a Production-Grade AI Agent from Scratch: A Practical Guide to MCP and LangChain
Learn how to build a production-grade AI Agent from scratch, covering the ReAct loop, Vue project demos, and the LangChain, LangGraph, and MCP tech stack.
What Is WorkBuddy? A Beginner's Guide to China's Codex Alternative for AI-Powered Office Work
WorkBuddy is China's Codex alternative — low barrier, free tier, and compatible with domestic office software. A beginner's guide to getting started with AI-powered workflows.
Auto-Generate Anime Short Dramas from a Script: A Complete Skills Pipeline Tutorial
A full walkthrough of the Skills drama auto pipeline: input a script and automatically generate characters, storyboards, prompts, and video. Covers models, 12-step workflow, API costs, and hands-on tips.
Complete Beginner's Guide to Codex: How OpenAI's AI Agent Actually Gets Work Done for You
Codex is OpenAI's AI Agent that goes beyond chat to actually write code, build websites, and create games. Learn how it works, how it compares to Claude Code, and how to get started.
Replicating Manus with Native Python: A Complete Guide to Multi-Agent Application Development
A deep dive into a hands-on multi-Agent development course that replicates Manus using native Python, MCP, and A2A — covering 7 learning stages, the MoreManus product, system architecture, and tech stack selection without framework black boxes.
GPT Researcher Alternative Claims 80% Token Cost Reduction
A developer released an open-source drop-in alternative to GPT Researcher claiming 80% Token reduction, seeking community validation. We break down the tech and how to evaluate it.
Using AI to Tackle Conway's Conjecture: Vibe Coding Enters the World of Mathematical Proof
React core contributor Dan Abramov used AI and vibe coding to attempt a proof of Conway's conjecture. Explore the potential, risks, and limits of AI-assisted math.