🍥

KnightLi Blog

记录并分享日常

Categories

137 pages

AI Tools

Curated posts and practical notes in AI Tools.

free-claude-code: Connecting Claude Code to OpenRouter, DeepSeek, and Local Models Through a Proxy

Compound Engineering Plugin: Turning AI Coding into a Plan, Execute, Review Engineering Loop

TradingAgents-CN: A Multi-Agent Financial Trading Research Framework for Chinese Users

qmd: Local Markdown Document Search for AI Agents

Claude Code Hooks Mastery: An Introduction to 13 Hook Lifecycle Events and Automation Control

Prompt Optimizer: An Open-Source Tool for Prompt Optimization, Testing, and MCP

Claude-Mem: Adding Cross-Session Long-Term Memory to Claude Code

Google LangExtract: Extract Structured Data from Long Text with LLMs

Claude.md Is Not Better When It Is Longer: How to Write Global Memory Files for AI Coding

Codex Is Starting to Control the Computer. What Does That Mean for the Future?

Why Does a Codex Skill Exist in the Directory but Still Not Show Up?

What Is the Difference Between ~/.codex/skills and Project .codex/skills in Codex

How to Choose Between GPT 5.5, Claude Opus 4.7, DeepSeek V4, and Qwen 3.6 Max

Ralph and Multi-Agent Collaboration: How to Keep AI Working Reliably Over Long Tasks

What Ralph Is: Turning Claude Code and Amp into a Repeatable Autonomous Development Loop

DeepSeek V4 Pro vs GPT-5.5: After Testing Frontend, Writing, and Coding, the Gap Feels Bigger Than Expected

How to Split Tasks Between ChatGPT, Claude, and Gemini: Choosing for Daily Use, Coding, and Special Capabilities

Why LLM APIs Charge by Tokens: A Clear Guide to Input, Output, and Context Costs

DeepSeek-V4 Preview Released: 1M Context, Two Models, and API Migration Notes

How to Fix Ollama Using CPU Instead of GPU

What Is NVIDIA nvbandwidth: How to Use This GPU Bandwidth Testing Tool

K-Nearest Neighbors for Beginners: Understanding Machine Learning Classification Through Neighbor Voting

OpenAI Releases GPT-5.5: Stronger Agentic Coding, Knowledge Work, and Research

How to Choose Common Embedding Models: OpenAI vs BGE vs E5 vs GTE vs Jina

What image vectorization is: from pixel images to searchable, analyzable vector representations

AI Terms Explained: Agent, MCP, RAG, and Token in Plain Language

How to Tune llama.cpp on 8GB VRAM: Why 32K Is Safer and 64K Needs KV Cache Quantization

Claude Code's Four-Part Environment Setup: CLAUDE.md, Rules, Memory, and Hooks Explained

llama.cpp GPU Performance Ranking: Full CUDA, ROCm, and Vulkan Scoreboards Explained with pp512 / tg128 / FA

What the Common GPU Inference Benchmark Metrics Actually Mean: FA, pp512, tg128, and Q4_0

A Practical Guide to Common Tensor Formats in LLMs: FP32, FP16, BF16, TF32, and FP8

A 16GB GPU Can Still Run 35B Models: VRAM Compression Strategies for MoE Models in LM Studio

Claude Code Multi-Agent Collaboration: How to Choose Between Subagents and Agent Teams

GPT Image 2 Officially Launches: From Generating Images to Commercial Use

nuwa-skill: Turning "distilling a person" from an idea into an executable workflow

OpenAI Introduces ChatGPT Images 2.0: Image Generation Starts Moving Toward Deliverable Output

Karpathy's 65-Line CLAUDE.md: Helping AI Coding Avoid Three Common Mistakes

Using Claude Code Quota More Efficiently: Models, Context, Caching, and /compact

rembg Project Notes: A Local Background Removal Tool

Ollama Multi-GPU Notes: VRAM Pooling, GPU Selection, and Common Misunderstandings

Google App for Desktop: Bringing AI Search to Windows

Gemma 4 E4B Uncensored vs Official: What Actually Changes

Deploy Hermes Agent Locally on Windows with WSL + Ollama and Connect Telegram

Where Does llama-cli -hf Save Hugging Face Models by Default

How to Fix SSL Certificate Verification Failed When llama-cli Downloads from Hugging Face on Windows

codex-quota Practical Guide: Local, Web, and Docker Usage with Original CLI Commands

Using Claude in VS Code: From API Setup to Page Generation

Claude Identity Verification: Why It Exists, What You Need, and How Data Is Handled

How Codex Usage Limits Work: 5-Hour Limits, Weekly Limits, and Credits

RAGFlow Project Notes: Features and Usage of an Open-Source RAG Engine