Your AI Agent Has Amnesia. Mine Keeps Receipts.

Months of shared memory across Claude, Codex and Antigravity — versions, retractions, and why append-only notes keep failing

TL;DR. Scattered Markdown notes kept sending my agents down paths we had already rejected. I built a shared Git-backed store (KYB) with versioned records and lifecycle states — active, archived, retracted. Query current state, history, or a time slice separately; replace wrong text instead of appending; separate finished work from wrong knowledge. Pinned to KYB v0.3.3, no controlled benchmarks — mechanisms and field notes below.

Before KYB, my coding agents already had memory: Markdown files scattered across different places. The flaw showed up whenever another agent returned to a workspace, found an older note, and mistook it for the active plan. In my experience, an agent would sometimes spend hours pursuing an approach we had already investigated and rejected. The file still held a perfectly reasonable case for the old approach, while the decision to abandon it lived somewhere else.