Ecosystem

The agent ecosystem

MCP servers, custom agents, skills, context files, hooks, and always on agents. Everything that makes your AI a complete operating system.

7

Entries

1

Categories

Concepts

The foundational ideas that make the agent ecosystem work.

🧠
Agent as Operating SystemConcept

The agent is not a tool you open sometimes. It is the operating system for your entire professional life: connected to everything, persistent, proactive, and always learning.

8 sections·1 min read
🔌
MCP (Model Context Protocol)Concept

A universal standard for connecting AI assistants to external services. Think of it as installing apps on your phone, but for your AI.

7 sections·1 min read
🎭
Custom AgentsConcept

Specialized AI personas with specific expertise, tools, and instructions. Like hiring specialists for your team: a code reviewer, a copywriter, a stock analyst.

6 sections·1 min read
📄
Context Files and MemoryConcept

Persistent knowledge that survives between sessions. Without context, Claude is a brilliant stranger. With context, Claude is a colleague who has worked with you for months.

6 sections·1 min read
🪝
Hooks (Automated Actions)Concept

Deterministic shell commands that fire on specific events, every single time. The difference between "please remember to format" and "formatting happens automatically, always."

5 sections·1 min read
Skills and Slash CommandsConcept

Encoded domain expertise that Claude applies on demand. Unlike agents (which are personas), skills are about knowledge and process. Think of them as instruction manuals for specific tasks.

6 sections·1 min read
🌐
Always On AgentsConcept

The other half of the system. 24/7 assistants running on a server, reachable through messaging apps, handling the daily flow while you sleep.

6 sections·1 min read