Tag
AI agent
AI agents are software systems that plan steps, call tools, and keep working across workflows, from support automation and office ops to data handling and coding. This tag tracks open-source frameworks, managed enterprise stacks, cost tradeoffs, and local deployment, where agents move from chat interfaces to operational software.
9 articles
Claude Code Advanced Patterns: 5 CLI Agent Design Tips
Most people use Claude Code for a week, come out with "it's basically ChatGPT with a terminal," and miss its real differentiator: persistent memory and a system that grows with use. This article compresses six months of production use into five patterns that matter — what CLAUDE.md is really for, what to store (and not store) in MEMORY, the composition logic behind Skills, three ways people misuse Subagent dispatch, and the trade-offs between tmux, MCP servers, and file buses for cross-CLI orchestration.
OpenClaw: How to build your own AI agent
OpenClaw is an open-source AI agent you can run locally, message from Telegram, and train to handle email, calendars, code, and more.
OpenClaw v2026.3.24: Reset Guide and Integrations
OpenClaw v2026.3.24 is still beta, but its reset flow, Ark Coding Plan support, and Feishu channels hint at a practical agent setup.
飞书开源CLI：AI Agent 直接管办公协作
飞书开源 CLI 提供 200+ 命令和 19 个 AI Skills，让 Claude Code、Cursor 直接操作日历、文档与消息。
OpenClaw安全风险与防护清单
OpenClaw已曝出1184个恶意技能包，23万+实例暴露公网。本文拆解风险、漏洞与防护清单。
Claude Skills Comprehensive Ranking: The 20 Most Essential Developer Tools in 2026
Claude Skills accelerates software engineering at scale. This guide covers official repositories, the top 20 community skills by category, highlight projects, quick lookup tables, and installation methods to help you find exactly what you need.
Harness Engineering: From Bridle to Operating System, The Missing Link in AI Agent Reliability
Harness Engineering is the discipline of designing external control frameworks for AI Agents. By integrating context engineering, architectural constraints, and garbage collection, it transforms unreliable large models into dependable production systems.
Kimi K2.5 review: stronger, still not a legend
Kimi K2.5 adds vision, coding, and multi-agent tools, but long runs, weak art direction, and paywalls keep it from elite status.
Anthropic's Claude AI Agent: A New Era of Task Automation
Anthropic's Claude AI can now autonomously complete tasks on personal computers, marking a significant step in AI agent capabilities.