A memory ledger that can prove nothing was edited and still forget
Memory That Forgets Bike4Mind Engineering A memory ledger that can prove nothing was edited and still forget How the memory layer keeps a tamper-evident, hash-chained event log and still honors "delete my data": salted commitments, per-principal keys that can be destroyed, a fence against in-flight writes, and beliefs that cool on their own. By Bike4Mind Engineering October 15, 2026 engineering · memory · security Opt-in today An AI that remembers things about you has two obligations that pull in opposite directions. It has to be auditable: you should be able to see what it believed, when it started believing it, and be sure nobody quietly edited the record afterward. And it has to honor "delete my data", which means the fact is actually gone, not hidden behind a flag. A log that nobody can alter and a log you can remove things from are, on first look, the same log wanting two different things. This post walks through how the memory layer in the open-source Bike4Mind core reconciles them: a hash-chained event ledger where a single fact can be destroyed and the chain still verifies. Where this stands today Mementos 2.0, the ledger-backed memory described here, is in the product but opt-in. It is an experimental per-user setting ( enableMementosV2 ) with no workspace-wide switch yet, so it is not on for anyone who has not turned it on. For a user who has, chat recall reads from the ledger, new memories are written to it, and the memory endpoints under /api/memo...
View as plain text