Hi, I'm Kevin An engineering-focused full-stack developer. I break complex systems into composable tools with Go + TypeScript/React, and I'm currently building bingo-code, an AI Coding Agent. More than calling model APIs, I care about making LLMs reliable engineering tools.
“Build tools I actually want to use.”

Use Git Worktree to assign an independent workspace to each AI Agent, enabling parallel development on the same repository with multiple branches and zero conflicts. This article introduces the complete multi-AI parallel workflow: worktree initialization, task decomposition principles, pitfalls and lessons learned, and scenarios where this approach is not suitable.

The fundamental gap between Hermes Agent and OpenClaw lies not in the number of features, but in their architectural philosophy: one is designed to "connect to everything," while the other is built to "remember everything." This article provides an in-depth analysis of their skill mechanisms, memory architectures, and cost comparisons to help you decide whether it is worth switching and how to deploy them in parallel.

OpenClaw transformed AI from a chat window into a 24/7 agent capable of operating local systems, but 8 CVEs and 42,000 bare-metal instances indicate its security cost is not low. This article dissects core mechanisms like Gateway, Heartbeat, and Lane Strategy, and provides alternative selection suggestions for ZeroClaw, NanoClaw, and PicoClaw.

A comprehensive analysis of OpenCode's architectural design, core functionalities, and implementation details, including an in-depth comparison with Claude Code, exploring the advantages of open-source AI programming tools in terms of cost, privacy, and scalability.

Skills can reduce token consumption by 75%. Its core value lies in "progressive disclosure" and "deterministic execution"—trading IO for tokens. This article deconstructs Skills' three-level loading mechanism to provide you with a technical decision tree for refusing blindly introduced complexity.

A compilation of installation, model support, advantages, and disadvantages for OpenCode, Crush, Qwen Code, Gemini CLI, Kimi CLI, Aider, Codex CLI, Grok CLI, Claude Code, and Copilot CLI, enabling you to easily select the most suitable AI coding partner.

Quickly install Claude Code via NPM or scripts, configure third-party models like DeepSeek and Zhipu GLM to reduce usage costs, and use the Claude Code Router (CCR) to build an intelligent routing system. The article details key technical points such as multi-provider management, dynamic routing strategies, request transformation, and cost optimization, and provides complete configuration examples and architectural designs.

Record of the upgrade process from Debian 12 to Debian 13 Trixie, with a detailed introduction to the main changes and highlight features brought by this version update.