🍥

记录并分享日常

Section

708 pages

Posts

Kimi K3 API Quickstart: Python, Streaming, Vision, and Tool Calls

How to run Grok Build locally after it is open source: Tutorial on connecting to MCP, Skills and Plugins

What are Grok Automations: What are the differences from ChatGPT Tasks and Claude scheduled tasks?

Synology file backup to Ubuntu: rsnapshot active pull and hard link snapshot tutorial

Synology Hyper Backup backup to Ubuntu rsync: module configuration, testing and troubleshooting

How to deploy Ollama OpenClaw locally: model selection, port, permissions and memory plug-in troubleshooting

How to connect TencentDB Agent Memory to OpenClaw: local long-term memory, log compression and traceable retrieval

How to install Archify into Codex/Claude Code: Generate architecture diagrams, flow charts and SVG from the warehouse

How does Orca run Codex and Claude Code in parallel: Worktree, task comparison and mobile approval

How Impeccable enables AI programming tools to audit the front end: /impeccable audit, design context and acceptance

Archify Architecture Diagram Skill Tutorial: Installation, diagram generation and troubleshooting of "wrong diagrams"

TencentDB Agent Memory local deployment tutorial: long-term memory, log compression and traceable recall

Orca Parallel Agent Workflow Tutorial: Use Git Worktree to run Codex and Claude Code simultaneously

Is the 5-hour limit of Codex temporarily cancelled: shared quota, Banked Reset and usage view

How to use ChatGPT Work: cross-application long tasks, scheduled tasks and desktop Codex workflow

How to use ChatGPT Sites: From prompt words to hosted website publishing and security checks

How to install Google Stitch Skills: Stitch MCP, Codex, Claude Code and design workflow configuration

How to Connect AI-Generated Frontends to a Design System with Astryx: React Components, Themes, and Acceptance Constraints

How Page-Agent Lets AI Operate Web Pages: Embedded GUI Agents, Form Automation, and Permission Boundaries

How to Install Chrome DevTools MCP: Debug Web Network, Console, and Performance with Codex and Claude Code

How OfficeCLI allows AI Agent to read and write Word, Excel and PowerPoint: Local Automation Guide

How does CubeSandbox configure an isolation environment for AI Agent: concurrent execution, permissions and cost trade-offs

How to install DesktopCommanderMCP: Claude Code file search, terminal control and differential editing configuration

Gemini Interactions API Migration Guide: How to troubleshoot after changing outputs to steps

How to access Grok 4.5 API: Responses API, price, EU availability and prompt cache settings

How to use ChatGPT Work: Scheduled Tasks, plug-in directory and long task approval guide

How to Use GPT-Live: Enable ChatGPT Voice, Choose a Mode, and Know the Limits

How to Use Claude Reflect: AI Usage Insights, Privacy, and Who It Suits

Above 4G Decoding should be turned on: BIOS settings, Resizable BAR, graphics card and NAS expansion card

Antimalware Service Executable High CPU What to Do: Defender Scans, Exclusions, and Security Boundaries

How to use Codex in VS Code: extension installation, login, workspace permissions and common errors

When does the Codex Usage Limit reset: 5 hours, weekly limit and how to read the Reset notification

How to install Taste Skill into Claude Code and Codex: SKILL.md placement, calling and front-end design examples

What to do if M3U Playlist cannot be played in VLC: link format, network and player troubleshooting

How to Filter iptv-org Channels by Country and Language: A GitHub M3U Playlist Guide

How to Open an iptv-org Playlist in VLC: M3U Links, Network Streams, and Troubleshooting

CC Switch Provider Switching Guide: Claude Code, Codex, and Local OpenAI-Compatible APIs

Where Are CC Switch Configuration Files? Fix Claude Code, Codex, and MCP Changes That Do Not Apply

9Router vs. CC Switch: Choosing AI Coding Routing or Configuration Management

9Router Claude Code Setup: API Base URL, Model Routing, and Common Errors

How to calculate the cost of running Agent on a consumer-grade graphics card: electricity bill, depreciation and cost per task

Local speech recognition Whisper NAS deployment: faster-whisper transliteration tutorial

Windows WSL deployment of local Agent tutorial: Ollama, Codex OSS and permission control

Whether the Ollama performance of NAS deployment is insufficient: how to judge the CPU, memory and graphics card

Local large model API for Codex usage tutorial: Ollama, LM Studio and vLLM

What to do if vLLM KV Cache has insufficient memory: video memory, context and concurrency troubleshooting

How to use LM Studio OpenAI compatible interface: Local API access tutorial

How to configure Ollama multi-model switching: resident, video memory and Modelfile tutorials

RTX 3060 runs the best quantized version of Qwen3: how to choose 12GB video memory

GPT-5.6 Released: How OpenAI Reframes Model Capabilities from Sol to Luna