Do Autonomous Agents Really Need an Orchestration Layer?

When you hear "autonomous agent," you imagine something that does everything on its own. It writes code, picks tools, and recovers from errors by itself. Frameworks like OpenClaw aimed for exactly that. After building my own autonomous agent, a different picture emerged. Autonomy isn't a ship that does everything on the open sea — it's a ship that sails out from a home port. Once it departs, it moves on its own. It remembers, learns, and makes decisions. But when it needs code generation or setup, it returns to its port: Claude Code. This article is about the "port-based autonomous agent" design that emerged through building Contemplative Agent. Series context (catch up in 30 seconds) Build Log — Security-first scratch build. Only external dependency: requests Evolution Log — Natural language becomes the architecture. Python is just the skeleton Sandwich — The alternating structure of markdown and code is the essence of LLM apps This article — Do you even need an orchestration layer? W