4 hard lessons from building a self-hostable, open-source AI agent runtime

When I started building omadia — an open-source (MIT), self-hostable runtime for composing AI agents out of plugins — I assumed the hard part would be the model: prompting, tool-calling, getting reliable output. It wasn't. The LLM bits were mostly solved problems. The parts that ate my time were isolation, data flow, and UX. Here are four lessons I wish I'd internalised earlier. 1. Memory isolation is a design problem, not a setting With a single agent you never notice. With several...