AI Agents

AI apps whose language model calls tools to get work done, such as Claude Code and Claude Desktop, and how to run them safely.

Topic Created Updated Also in German: KI-Agenten

Reviewed by adrian on

An AI agent is an application whose language model does not only answer but calls tools to get work done: it reads and writes files, runs commands, searches the web or uses services through a protocol such as MCP. Some agents work only when asked, others run all the time and act on their own, which makes their permissions the main question. This topic collects how agents work, how they are set up and how they are kept safe.

Based on

More on this

Covered in

  • Hermes Agent on a VPS Behind WireGuard Guide: Hermes Agent in Docker on the VPS yaksha, dashboard behind Caddy and reachable only through WireGuard, container cut off from the tunnel network.
  • Securing a Persistent AI Agent How to let an AI agent work on its own without handing it the keys: OpenAI's five safeguards explained, and how I apply them to my own agents.

Part of

  • AI / Language Models What I use language models for: agents, local models, RAG and small programs in which a model handles one task.

See also

  • LLM Wiki Andrej Karpathy's pattern for personal knowledge: an LLM agent reads each source once and works it into a growing set of interlinked notes.
  • Model Context Protocol Open protocol through which AI apps such as Claude Code and Claude Desktop connect to servers that offer them tools and data.

Show in the graph view