Writing technical docs and need a system architecture diagram? The traditional route is opening draw.io, hunting for icons, dragging shapes, drawing connectors, aligning everything — the whole process takes at least 10 minutes. Next AI Draw.io compresses that to a single sentence: describe what you need in plain English, and the AI generates a professional draw.io-format diagram right in your browser. It supports the MCP protocol, so you can call it directly from Claude Code — sketch the diagram while you’re writing the code.
Understanding AI Models vs Tools — What's the Difference?
Series navigation: 01 What is AI | 02 Machine Learning | 03 Deep Learning | 04 Neural Networks | 05 NLP
Tokens Demystified: How LLMs Read Text
If you’re new to large language models, you’ve probably seen messages like “consumed XXX tokens” or “exceeded token limit.” A token is the smallest unit an LLM uses to process text. The model doesn’t read text character by character or sentence by sentence. Instead, it first splits text into chunks of tokens, then processes them chunk by chunk. There are solid technical reasons behind this design.
CloudCLI UI: A Web-Based GUI and Cloud Solution for Claude Code
CloudCLI UI (also known as Claude Code UI) is a Node.js + React web application that provides a unified graphical interface for Claude Code, Cursor CLI, Codex, and Gemini CLI. Unlike desktop apps, it runs in the browser, works on mobile devices, and offers cloud hosting options. The project is open-sourced by the CloudCLI team, built with Express + WebSocket + React, and writes configuration directly to the ~/.claude directory, staying fully in sync with the CLI.
opcode: A Desktop GUI for Claude Code
opcode is an open-source desktop application built by the Asterisk team, constructed with Tauri 2 + React, providing a full graphical management interface for the Claude Code CLI. It transforms the command-line tool into an intuitive desktop experience, supporting custom Agent creation, session management, cost tracking, and timeline rollback. All data stays local with no cloud dependency.
Making Sense of the AI Landscape: LLMs, Agents, MCP, and More
Between 2024 and 2025, new AI concepts have been arriving at a relentless pace. ChatGPT, Claude, DeepSeek, Agent, MCP, Vibe Coding — these names show up everywhere in tech discussions. A lot of people I know want to understand what each one means and how they relate to each other, but the information overload makes it hard to get a clear picture. This article aims to build a mental map that connects the core concepts — LLM, Agent, Skills, MCP — and shows how they fit together. Once you have this framework, any new concept becomes easier to place, and you’ll be in a better position to pick the right tool for your problem.
Vector Similarity Search: From Math to Algorithms
The core problem a vector database solves is this: given a query vector, find the K most similar vectors in the database fast. This breaks down into three layers — the mathematical definition of similarity, the algorithm design for approximate nearest neighbor search, and the engineering optimizations around index structures and storage. This article covers the first two layers in depth: the math behind similarity measurement and the mechanics of the core search algorithms.
Deep Dive into Vector Databases
When building RAG (Retrieval-Augmented Generation) applications, a vector database is the core component you can’t avoid. There are plenty of products on the market (Milvus, Qdrant, Weaviate, Chroma, Pinecone), and each one claims to be the best. This article goes from底层 principles to practical selection, with a重点 analysis of Chroma and Milvus as representative products, to help you make the right choice for your specific scenario.
Production-Grade PDF Processing for RAG Systems
I have been working on a RAG project recently and ran into plenty of pitfalls with PDF processing. Real-world PDFs come in many forms: contracts, financial reports, technical manuals, academic papers, and even scanned documents. The content is not just text — it includes tables of contents, tables, flowcharts, headers and footers, and multi-column layouts. Naively extracting raw text and feeding it into RAG will almost certainly produce broken, duplicated, context-free garbage chunks. Below is a four-layer architecture for PDF RAG, a methodology I developed through hands-on practice.
Learning Guide: 10+ Open-Source Agent Projects to Study
The previous post systematically covered the essential Agent programming glossary. With that conceptual foundation in place, the next step is diving into real project code.
This article recommends 10+ open-source Agent projects worth studying in depth, covering single Agents, multi-Agent systems, Code Agents, and production-grade platforms. For each project you’ll find: star count, learning value, key files, and which stage of learner it suits. By the end, you’ll have a clear learning roadmap: where to start, how to go deeper, and what you’ll be able to build.