“This is a data-durability bug in the AgentDB persistence layer: a long-running store should not be one interrupted/concurrent flush away from total loss.”
Quote · github.com
From “AgentDB (sql.js) corruption: 185MB memory.db malformed under concurrent daemon+MCP writes”, found 2026-10-14.
A shared memory database with about 16,700 entries became unreadable, then broke again about half an hour after a restore. PR #2585 added atomic flushes; cross-process locking was left for later.