Why your AI agent gets dumber over time (and how to fix memory drift)

Last week, a coding agent in a test repo did something weird: it opened the right files, referenced the wrong API version, and confidently wrote code for a migration we had already rolled back. Nothing was “broken” in the usual sense. The prompts were fine. The tools were available. The model was good. The problem was memory drift. If you’ve built anything with long-running agents, you’ve probably seen it too: the agent starts strong, then gradually retrieves stale facts, outdated decisions, or half-relevant chunks from old work.