Browse All Topics: AI Agents, MCP, and Claude Code Guides

Model Context Protocol connects AI agents to your tools and data. These guides cover the stateless 2026 spec, the code execution pattern, and MCP servers.

Claude Code is Anthropic's terminal coding agent. These guides cover CLAUDE.md files, model routing, hooks, cost tracking, and keeping workflows stable.

Coding agents are LLMs that read, write, and run code from your terminal. These guides compare Kimi K3, GLM-5.2, Gemini, GPT-5.6, and Qwen, plus their CLIs.

Agent platforms host, run, and grade AI agents for you. These guides cover Claude Managed Agents, the ant CLI, Claude Tag in Slack, and self-hosted bots.

AI agents add new attack surface: prompt injection, hallucinated packages, and gateway CVEs. These guides cover each attack and the defenses that hold.

Running AI agents in CI/CD needs non-interactive auth, cost caps, and least privilege. These guides cover GitHub Actions, AI code review, and version pinning.

Local inference runs open-weight models on hardware you own at zero token cost. These guides cover GLM-5.2, Gemma 4, Apple Core AI, and the RAM you need.