Tools
55 articles. 閱讀中文版
OpenGCUA Guide: The Open-Source Approach to Letting AI Actually Use a Computer
OpenGCUA is an open-source generalist computer-use agent from the Tongyi-MAI team. This guide breaks down its accessibility tree, code execution, and background operation design, checks the paper's 82-task numbers, and gives macOS install steps, three adoption paths, and an isolation plan for its arbitrary-code-execution risk.
ArtCraft Deep Dive: The AI-Generation App (macOS) and Where It Fits
A hands-on breakdown of ArtCraft v0.41.0: the desktop app's data model, task store, cost and account, and how it hands off to DesignCraft/OfficeCLI via files — with a table of verified facts.
DesignCraft Deep Dive: Layout and Publishing with designcraft-cli
A hands-on guide to designcraft-cli v0.5.0: the nine top-level subcommands, the file.new document model, headless rendering, the App control port, script automation, MCP integration and benchmarks — with four real rendered pages.
OfficeCLI Deep Dive: Control Word, Excel and PowerPoint from the Command Line
A hands-on guide to officecli v1.0.156: the L1/L2/L3 three-layer fallback model, resident mode, atomic batch edits, interactive watch editing, specialized skills and MCP integration, with real rendered screenshots.
Automating Comparable Company Analysis: Run an Entire Sector in One Pass
The difficulty in comparable company analysis is not the arithmetic of multiples but the basis: fiscal year, currency, one-off items, and EV composition can all let two companies' numbers contaminate each other. This article breaks down the criteria for selecting peers, six categories of basis-unification rules, and the traps in choosing multiples, and gives a five-stage automation pipeline design with executable code, from data extraction to outlier handling.
Connecting Your AI Agent to Feishu/Lark: A Beginner's First Enterprise Channel
Use Hermes Agent to connect an AI agent into Feishu or Lark: scan a QR code to create the app, a persistent WebSocket connection with no public IP needed, set the allowlist, send the first message. The one channel with every box ticked in the capability matrix — this is the beginner path; deeper configuration links out to the advanced article.
Connecting Your AI Agent to Telegram: The Simplest First Channel
Use the Hermes Agent gateway to connect a terminal-capable AI agent into Telegram: create the bot with BotFather, set the allowlist, install it as a persistent service, send the first message — and understand who can talk to your bot and where to look when something breaks.
Connecting Your AI Agent to WeChat: Capability Boundaries, Account Risk, and the Full Steps
Use the Hermes Agent weixin adapter to connect an AI agent into personal WeChat: iLink QR-code login, tightening the DM policy, collecting user IDs, starting the gateway. Includes the capability matrix, an honest assessment of the terms-of-service risk, and fixes for common errors.
Connecting Your AI Agent to WhatsApp: Two Paths, Bridge and Official Cloud API
Hermes Agent reaches WhatsApp two ways: the Baileys bridge (scan a QR, personal account, risk-control exposure) and Meta's official WhatsApp Cloud API (business account, webhook, no ban risk). This article teaches you how to choose, how to connect, and who gets to talk to your bot.
DCF Assumptions and Sensitivity Analysis: Make the Valuation Challengeable
The value of a DCF is not in computing one number but in whether the assumptions behind it can be examined, challenged, and recomputed. Using a hypothetical model for teaching, this article demonstrates the assumptions register, the three-stage cash-flow structure, the composition facets and trade-offs of WACC, the risks of the two terminal-value methods, the design of single-factor and two-factor sensitivity matrices, and how to present a valuation as a defensible range rather than a fragile single point.
The First Ten Minutes After Installing an Agent Tool: A Seven-Item Verification Checklist
Just installed Cursor, Claude Code, Codex, OpenClaw, Hermes, or any AI Agent tool? Don't assign work yet. Spend ten minutes on seven verifications: it runs, it reaches the model, it reads files, it writes files, permission boundaries, one real task, and where the logs are. Tool-agnostic.
Your First LLM API Call: Tokens, Billing, and Common Errors
Send your first LLM request with Python's openai SDK: understand the division of labor among system, user, and assistant message roles; the trade-offs of temperature, max_tokens, and streaming; token billing concepts and usage estimation; and finally, a troubleshooting guide for the errors every beginner will meet.
Installing Claude Code: A Getting-Started Path for the Terminal Agent
Anthropic's official terminal coding agent Claude Code, from system requirements, four install methods (native install script, Homebrew, WinGet, npm), the verification command, and browser sign-in, to permission modes and your first change. Every step spells out the output you should see and the real error messages listed in the official docs.
Installing the OpenAI Codex CLI: Sign-In, Permissions, and Your First Task
OpenAI's terminal coding agent Codex CLI, from system requirements, three official installation methods, ChatGPT-account sign-in and API-key sign-in, to the three /permissions presets and non-interactive mode. Every step spells out the output you should see and flags which commands I could not verify against the official documentation.
Installing Cursor: From Download to Your First AI-Assisted Edit
Follow this guide and you'll end up with a working Cursor on your machine: signed in to an account, a real project open, having watched it change a line of code with a diff you see yourself, and the command-line Cursor CLI installed. Every step spells out what you should see and what failure looks like.
Installing DeepSeek Harness: Two Paths, Web GUI and Terminal
How to install DeepSeek Harness (dsh), DeepSeek's official open-source agent runtime: launch the Web GUI with npx @deepseek-ai/dsh web, set your key under Settings → Models, choose a workspace, run your first task, plus the terminal-only route via the headless profile. Every step spells out the expected output and the real errors the official docs list.
Doubao Work Installation Guide: Downloading the Desktop Client, Signing In, and Your First Work Task
Install ByteDance's Doubao Work desktop client step by step: confirm the Windows and Mac configuration requirements, download and install, sign in and claim the trial benefit, then use Work Task mode to complete your first AI Agent task and accept the deliverables and quota.
Hermes Agent Installation Guide: Two Paths, Desktop App and Command Line
Step-by-step installation of Nous Research's open-source Hermes Agent: the macOS and Windows desktop bundles, the Linux/macOS/WSL2 command-line script, the Windows PowerShell and Termux paths, plus first launch, model configuration, the health-check command, and official troubleshooting.
OpenClaw Installation Guide: One Command to Your Own AI Agent Gateway
Step-by-step installation of the open-source agent framework OpenClaw: the official install script, the first-run setup wizard, installing the Gateway as a background service, opening the web console, and verifying the installation with your first message — plus fixes for the common PATH and npm errors.
Installing Trae: Running Both IDE Mode and SOLO Mode Once
ByteDance's AI IDE Trae (TraeCode), from downloading, initial setup, sign-in, and opening a project, to running one task each in IDE Mode and SOLO Mode and setting the permission mode. Every step spells out what you should see on screen, plus the real errors and fixes listed in the official docs.
WorkBuddy Installation Guide: From Download to Your First Completed AI Task
Install Tencent's WorkBuddy desktop app step by step: confirm the Windows and Mac system requirements, download and install, sign in by scanning a WeChat QR code, then create your first AI task and check the deliverables. All GUI operations, with no command-line background needed.
Set Up Your LLM Dev Environment in Five Minutes
Build a development environment that can call an LLM API from scratch: installing Python, virtual environments, getting an API key, and managing environment variables, then verifying the whole chain with a single curl command. Complete commands for both macOS and Windows, with a focus on keeping your key safe and out of git.
Announcement and Research-Report Monitoring Agent: Alert Me Only When Something Actually Changes
How to design a monitoring agent that notifies you only on substantive change: three classes of monitoring target, fetching and deduplication strategy, the three gates that filter noise, where summary ends and impact assessment begins, tiered delivery, and the balance between never missing something material and never causing alert fatigue.
Terminal, Shell, CLI: The Difference Between the Three Terms, and Ten Survival Commands
The first line of most AI-tool install guides is 'open a Terminal,' but nobody explains how Terminal, Shell, and CLI actually differ. This article separates the three terms, gives you ten commands that really are enough, shows you how to read error messages, and covers the habit that costs beginners the most.
What Is an API Key: It's Both Your Identity and Your Wallet
An API key is a string that tells a remote service 'this request is yours, and the bill goes to you.' This article explains why it's a secret, where it belongs (environment variables or .env — never a chat window), what to do on leakage, why it's usually wired directly to money, and a distinction most beginners miss: logging into the web version is not the same as having an API key.
Your First Agent: A Hello World That Uses Tools
Hand-write an Agent that actually does things, without any framework: it checks the weather, does arithmetic, and loops on its own until the task is complete. A step-by-step breakdown of the six steps of the Agent loop, its termination conditions, and the common pitfalls — once you've written it, you'll understand what frameworks do for you.
PaddleOCR in Practice: Extracting Hong Kong Stock Annual Report Financial Data in 83 Seconds
A hands-on test of Baidu PaddleOCR, the open source document AI engine with 81K Stars. PP-OCRv5 with 96.5% accuracy extracted 102 text regions from a Hong Kong stock annual report P&L page, discovered a KMeans clustering bug (n_clusters=0) in the PP-StructureV3 Transformers engine, built a custom DBSCAN row and column clustering parser, and completed automatic structuring of three financial statements end to end in 83 seconds.
Webb-Site: The Essential Hidden Treasure for Hong Kong Stock Research, a One-Click Tool to Get Annual Report PDFs for All Listed Companies
David Webb's independent Hong Kong stock database webb-site.com is an overlooked treasure. It directly provides PDF links from hkexnews.hk, listing on one page all annual reports and interim reports of a company from listing to present, completely bypassing hkexnews's internal stock ID restrictions. This article includes a complete usage tutorial, a known ID mapping table, and a batch download solution.
Academic Research Skills Deep Technical Breakdown: How 45+ Agents Collaborate to Complete the Full Workflow from Literature Review to Peer Review
Complete technical analysis of the GitHub Trending #3 project Academic Research Skills: the architecture design of a 13-Agent research team, a 12-Agent paper writing pipeline, and a 7-Agent review panel, plus innovative mechanisms such as Socratic dialogue, integrity gates, and style calibration.
AI Engineering from Scratch Deep Dive: 435 Lessons × 20 Stages
Complete breakdown of GitHub Trending #5 project AI Engineering from Scratch: curriculum structure under the Build, Don't Import philosophy, six-beat rhythm teaching method, 20-stage technical roadmap, in-depth analysis of Phase 14 Agent engineering, and its impact on AI engineers' career development.
CodeGraph Deep Technical Breakdown: How to Save AI Coding Agents 35% in Costs and Cut Tool Calls by 70%
Complete technical analysis of the GitHub Trending #1 project CodeGraph: the architecture design of pre-indexed code knowledge graphs, the tree-sitter AST parsing pipeline, the MCP tool layer, performance comparison data against native Agents, and the real impact on Claude Code/Hermes Agent.
Complete Comparison of Top 10 Vector and Full-Text Databases: MemoryHub Backend Storage Selection Guide
An in-depth review of ten databases, including Qdrant, Chroma, LanceDB, SQLite-vec, FAISS, Redis, PostgreSQL (pgvector), Elasticsearch, MongoDB Atlas, and Neo4j, in AI memory system scenarios, covering performance, deployment difficulty, resource consumption, and use cases.
MemoryHub Practical Installation and Complete Usage Guide: From Zero to Four Platform Automatic Memory Capture
A step by step guide to installing MemoryHub v2.0: from Docker environment preparation, one click pip installation, four platform MCP configuration, Dashboard usage tips, to the complete process of daily maintenance and troubleshooting.
Complete Comparison of 15 Native Search Engines: In-Depth Analysis from Indexing Mechanisms to Application Scenarios
A comprehensive review of 15 native search engines supported by OpenClaw: indexing sources, API pricing, latency, Chinese language support, stability, and the best choice for each scenario.
Brave Search API Configuration and Tavily Scenario Comparison
Configuration of Brave Search API in a three-tier Agent framework, plus a scenario selection guide for Tavily vs Brave.
A Deep Dive into Claude Code
From installation and configuration to advanced techniques, fully master the Claude Code CLI tool, actually powered by DeepSeek V4 / ModelStudio, to boost everyday development efficiency.
DeepSeek V4 Flash / V4 Pro API Best Practices and Performance Comparison
Complete guide to the DeepSeek V4 series models: comparing performance, pricing, and use cases of V4 Flash vs V4 Pro, with API call examples and cost estimates.
Financial Data API Research: Injecting Market Data Capabilities into Agent Frameworks
Research on financial data APIs suitable for Agent frameworks: Hong Kong stocks, US stocks, macroeconomic data, with plans to integrate financial data analysis capabilities into OpenClaw.
Comparison of Other Inference Frameworks: A Complete Guide to llama.cpp, MLX, and ExLlamaV2
An in-depth comparison of three major local LLM inference frameworks: llama.cpp (GGUF), Apple MLX, and ExLlamaV2, covering installation, performance, and use cases.
LiteLLM Proxy Multi Model Routing in Practice
Use LiteLLM Proxy to centrally manage multiple LLM backends such as DeepSeek, ModelStudio, Ollama, and more: load balancing, cost tracking, fallback configuration.
LM Studio Installation and Usage Guide: GUI Local LLM Management
Complete LM Studio guide: download, manage, and run local LLMs on Mac through a graphical interface, supporting GGUF and MLX formats and providing an OpenAI-compatible API.
Three-Engine Search Strategy: DuckDuckGo + Tavily + Brave Complementary Configuration Guide
Role division, scenario selection, and cost comparison of three search engines in an Agent framework. DuckDuckGo is free and fast, Tavily provides AI summaries, Brave covers news and communities comprehensively.
oMLX + Qwen3 Coder Next Local Deployment Guide (Replacing Ollama)
Running Qwen3 Coder Next natively on M3 Ultra with oMLX, fully replacing Ollama: why drop Ollama, oMLX advantages, installation steps.
oMLX Installation and Usage Guide: Running MLX Models Natively on Apple Silicon
Complete oMLX installation and usage guide: running MLX format models natively on M3 Ultra, covering installation, model import, performance comparison, and optimal configuration.
Cross-layer Configuration of Tavily Search API in Agent Frameworks
Configuration methods and usage scenarios for the Tavily AI Search API across three frameworks: Hermes Agent, OpenClaw, and Claude Code.
Complete Guide to vLLM Deployment and Performance Tuning
vLLM high-performance LLM inference engine deployment guide: installation, configuration, PagedAttention principles, performance benchmarking.
Web Fetch and Web Scraping in Agent Applications
Configuration and scenario guide for using Web Fetch / Puppeteer / fetch_url to retrieve web content in a three-tier Agent framework.
Complete Development Environment Setup on Mac Studio M3 Ultra
Build an AI development environment from scratch on Mac Studio M3 Ultra (512GB RAM): system configuration, Homebrew installation, basic toolchain, and performance tuning.
Open Design Critique Skill Guide
5 dimension expert level design review: philosophical consistency, visual hierarchy, detail execution, functionality, innovation, each scored 0 to 10, with a radar chart and action list as output.
Open Design DCF Valuation Skills Guide
Discounted cash flow valuation and intrinsic value analysis for listed companies: DCF models, fair value, target price, discount rate, sensitivity analysis.
Open Design Gamified App Skills Guide
Multi-frame gamified mobile prototype: three iPhones side by side showing the cover, quest list and quest details, with an XP level system, bottom Tab Bar and pastel quest tiles.
Open Design Hatch Pet Skill Guide
Create Codex compatible animated sprite pets from character design drafts, screenshots, and generated images: 8×9 atlas, transparent unused cells, per-row animation prompts, QA contact sheet, preview video, and pet.json packaging.
IB Pitch Book Skill Guide
Investment Banking Pitch Book: Trading Comparables / Precedent Transactions / Valuation Football Field / DCF Sensitivity Analysis / Strategic Options Matrix / Process Recommendations, 10-page standard structure, with built-in compliance disclosures.
Open Design: Complete Categorized Catalog of 118 Skills
Complete index of the Open Design skill system: 118 skills, 146 design systems, covering presentations, web pages, dashboards, mobile apps, video, documents, and other full-scenario use cases.
Zhangzara Design Style Comparison
A visual comparison of 32 Zhangzara HTML presentation styles, from 8-Bit Orbit to Vellum, with all design styles at a glance.