#Prompt Cache
538 related articles
·4 min
Building a Tide App Mini Program with Codex in 4 Sessions: A Hands-On AI Coding Agent Tutorial
Learn how to build a Tide App WeChat Mini Program in 4 sessions using OpenAI Codex AI coding Agent, covering agents.md setup, Plan Mode, domain config, and more.
Read more →
·4 min
KV Cache Saves 20x on Costs: The Underlying Principles and Practical Tips for LLM Inference Optimization
Deep dive into how KV Cache reduces LLM API costs by 20x. From Transformer attention matrix multiplication overhead to prompt caching best practices, understand the fundamentals of AI inference cost optimization.
Read more →
·3 min
Ponytail Plugin: The Minimalist Philosophy That Makes AI Coding Agents Write Less Code
Ponytail is a minimalist plugin for Claude Code that uses YAGNI principles and a decision ladder to cut AI-generated bloat. Tests show 47%-77% cost savings and 94% less code.
Read more →
·3 min
Workstyle Memory Bridge: Making AI Remember How You Work
Explore how Workstyle Memory Bridge uses Slot+Scope unique keys, provenance tracking, and verifiable deletion to solve AI coding assistants' persistent memory loss of collaboration preferences.
Read more →
·3 min
DeepSeek ZOI In-Depth Review: An Open-Source Local AI Agent Desktop Workspace
In-depth review of DeepSeek ZOI open-source desktop app covering Code Mode coding Agent, Write Mode, Cone Runtime optimization, setup guide, and cost comparison with Codex and Claude Code.
Read more →
·3 min
AI Agent Loops in Practice: Four PRs Auto-Merged While I Slept
From manual AI prompting to building automated loops — let Agents prompt, review, and merge code themselves. A real-world case: one message triggers four PRs auto-reviewed and merged overnight.
Read more →
·4 min
Dark Mode for WeChat Mini Programs: One-Click Color Scheme Generation with Pencil MCP
Complete guide to WeChat Mini Program dark mode: from generating dark color schemes with Pencil MCP and AI image generation, to building a Theme.js switching architecture with CSS variables and system dark mode detection.
Read more →
·4 min
Claude Code Controlling Unreal Engine 5: Two Free Plugins for AI Game Development
Learn how to connect Claude Code to UE5 for free using Unreal Cloud and Vibe UE plugins. AI builds game levels, edits Blueprints, and adjusts materials.
Read more →
·3 min
New Book Breakdown: "Claude Code in Practice: The Way of Harness Engineering" — Master AI Programming Engineering in Ten Chapters
Deep breakdown of the new book on Claude Code engineering, covering Harness concepts, four-layer architecture, five-layer memory, sub-agents, hooks, MCP protocol, and CI/CD integration.
Read more →
·4 min
DeepSeek Forms Harness Team: AI Coding Competition Enters the Second Half
DeepSeek forms a dedicated Harness team to rival Claude Code. Analysis of the four-layer architecture, three core advantages, and 40x cost edge driving AI competition from model wars to engineering deployment.
Read more →
·3 min
Claude Code's Hidden Advantages Explained: Design Choices Every AI Coding Tool Should Copy
Deep dive into Claude Code's leading design in agentic coding: skill script execution, CLAUDE.md imports, remote control, dynamic workflow orchestration, and why Cursor, Codex and others should adopt these features.
Read more →
·4 min
Hands-On Tutorial: Building an AI Trending News Dashboard from Scratch with Claude Code
Learn to build an AI trending news dashboard from scratch with Claude Code — no coding required. Covers CC setup, domestic model integration, and full-stack development.
Read more →
·4 min
HAMAS Multi-Agent Framework in Practice: A Guide to Building 5 AI Personas Working in Harmony
Learn how to build a multi-Agent AI team with the HAMAS framework: 5 role configurations, Skill mechanisms, gradient model scheduling, and solutions for AI hallucination and deception.
Read more →
·3 min
LangGraph Beginner's Guide: Core Advantages, Common Misconceptions, and Deployment Practices Explained
A comprehensive guide to LangGraph's three core advantages, its relationship with LangChain, short-term and long-term storage mechanisms, and deployment strategies for development and production environments.
Read more →
·3 min
DeepSeek Open-Sources a Terminal Coding Agent: A Claude Code Alternative with 38K GitHub Stars
DeepSeek's open-source terminal coding Agent: zero dependencies, million-token context, 20 parallel sub-agents, 38K+ GitHub Stars. A detailed comparison with Claude Code.
Read more →
·3 min
Vibe Coding in Practice: The Right Way to Communicate with AI — Just Ask When You Don't Understand
Learn effective AI communication techniques for Vibe Coding: how to ask when you don't understand, discover plan gaps through follow-ups, and align on terminology with AI.
Read more →
·3 min
GML 5.2 Multimodal Upgrade Hands-On: Full Validation with DeepSeek V4
Hands-on testing of GML 5.2 and DeepSeek V4 multimodal upgrades on OneBlockBase, covering vision-text workflows, safety mechanisms, and deployment tips.
Read more →
·3 min
DeepSeek + Cline Setup Guide: A $1.50 Alternative to $20/Month AI Coding Subscriptions
Step-by-step guide to configuring DeepSeek API with VS Code plugin Cline, including API Key setup, Plan/Act dual-model strategy, and project management files for a $1.50 AI coding alternative.
Read more →
·3 min
Multi-Agent Cost-Cutting Guide: 4 Documents to Slash 60-80% of Your Token Spending
Multi-agent bills out of control? This article breaks down two core token cost pain points and provides 4 actionable documents to cut multi-agent task costs by 60-80%.
Read more →
·3 min
Building a DeepSeek Agent from Scratch: Principles, Token Optimization, and Bootstrapped Development
Learn how to build a DeepSeek V3 AI Agent from scratch with zero dependencies, covering Agent loop mechanics, token optimization, cache hit strategies, and bootstrapped development.
Read more →