#sandboxed code execution
132 related articles
·3 min
Anthropic Skills Mechanism Explained: An Open Standard for Giving AI Installable Skill Packs
Deep dive into Anthropic Skills (nearly 150K GitHub stars): skill.md structure, progressive loading, ready-to-use skills ecosystem, and the cross-tool open standard for AI skill packs.
Read more →
·2 min
Complete Tutorial: Image2 + Codex to Generate Editable Figma Design Files
Learn how to use ChatGPT Image2 to generate high-quality UI mockups and OpenAI Codex to convert them into editable Figma vector files in three steps.
Read more →
·2 min
OpenAI Codex Record & Replay Explained: Show It Once and the AI Learns
OpenAI Codex launches Record & Replay: demonstrate a workflow once and the AI learns to repeat it independently. A deep dive into how it works and where it applies.
Read more →
·3 min
The Complete Guide to OpenAI Codex CLI: From Installation and Configuration to Enterprise-Level Practice
In-depth guide to OpenAI Codex CLI: covering installation, agents.md design, multi-agent collaboration, MCP protocol integration, and a RAG customer service project.
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 →
·3 min
Deep Dive into Claude Code's Source Architecture: Harness Engineering and Seven Core Mechanisms
Deep analysis of Claude Code's leaked source architecture, covering TypeScript stack choices, Harness architecture's seven core mechanisms, tool call management, and context optimization.
Read more →
·3 min
Claude Code Permission Management Fully Explained: Configure It Right Before You Trust It
Deep dive into Claude Code's four permission categories (Bash, File, MCP, WebFetch), two-level config system, and three common pitfalls for safe AI coding.
Read more →
·3 min
Kimi Code Open-Source Hands-On Review: Installation, Feature Comparison & Cost Analysis
Hands-on review of Moonshot's open-source Kimi Code terminal AI coding tool, covering one-command installation, Ink framework architecture, VS Code plugin mode, and comparisons with Claude Code and Gemini CLI.
Read more →
·3 min
Enterprise AI Agent Architecture in Practice: Sandbox Isolation and Skill Management Explained
Deep dive into enterprise AI agent architecture covering HARIS task decomposition, sandbox isolation, Skill persistence, MCP tool integration, and user-level memory systems.
Read more →
·4 min
Developing Figma Plugins with Codex: A Zero-Code Guide for Designers
Learn how to build Figma plugins with OpenAI Codex — no coding required. Covers project setup, quota management, Plan Mode, hands-on development, and publishing tips for designers.
Read more →
·3 min
Freely Switch Between Claude/DeepSeek and Other AI Models in Codex: CPA Deployment Guide
Learn how to use CLI Proxy API (CPA) to aggregate Claude, DeepSeek, Grok, and Gemini models into OpenAI Codex via VPS deployment, Docker setup, and Codex++ integration.
Read more →
·3 min
Claude Sonnet 4 Invents Its Own Browser Automation: The Wild Debugging Journey of a CSS Bug
Simon Willison shares how Claude Sonnet 4 (Fable) autonomously invented PyObjC screenshots, built a CORS server, and penetrated Shadow DOM to debug a CSS bug — revealing both tool-making power and security risks.
Read more →
·2 min
Major NotebookLM Upgrade: Powered by Gemini 3.5, Cloud Computing Environment Unlocks Deep Research
NotebookLM gets a major upgrade with Gemini 3.5 and Antigravity technology, adding a secure cloud computing environment with 100+ software skills, evolving from an AI note tool into an intelligent research platform.
Read more →
·1 min
v0 Introduces Permission Modes: Enhanced Security Controls for the AI Code Assistant
Vercel's AI coding tool v0 launches Permission Modes with three levels — Ask Every Time, Smart Judgment, and Free Execution — giving developers fine-grained control over AI operations.
Read more →
·3 min
Codex Powers Hedge Fund: Economic Analysis Cut from 2 Days to 30 Minutes
Balyasny Asset Management adopts OpenAI Codex and o3/4o models, cutting economic analysis from 2 days to 30 minutes with 97% daily active AI adoption.
Read more →
·3 min
OpenAI Codex Deep Dive: How AI Coding Agents Are Reshaping the Entire Software Development Lifecycle
Deep dive into OpenAI Codex's core capabilities and real-world applications, covering automated coding, compliance reviews, and security detection — revealing how AI coding agents boost team efficiency by 50%.
Read more →
·5 min
CherryStudio + MCP: Tutorial for Building Automated AI Agents and Local Knowledge Bases
Complete guide to building automated AI agents with Cherry Studio and MCP protocol, covering environment setup, MCP Server configuration, web scraping, Shell execution, and Ollama local knowledge base deployment.
Read more →
·2 min
OpenAI Codex Cloud Task Delegation: The Complete Workflow from VS Code to PR
A detailed guide to OpenAI Codex extension's cloud task delegation, covering the complete workflow from initiating cloud coding tasks in VS Code to reviewing changes and creating Pull Requests.
Read more →
·3 min
OpenAI Codex IDE Extension in Practice: A Complete Guide to AI Programming in VS Code
A detailed guide to OpenAI Codex IDE extension setup and usage, covering Agent/Chat modes, Modal component code generation, and GPT-5 model comparison for efficient AI-assisted programming in VS Code.
Read more →
·2 min
Claude Code + Codex: The Most Reliable Division of Labor — A Three-Phase Approach of Planning, Execution, and Review
A detailed guide to the Claude Code and Codex collaborative workflow: Claude Code handles architecture planning and code review, while Codex handles execution. Boost dev efficiency through standardized handoffs.
Read more →