Skip to the card

Card 020 of 9812026-09-22 issue

Observed arrival · 2026-09-22

Agent Memory Integrity: a security scorecard for AI agent memory

agentmemoryintegrity.org Visit website
Editorial interest 84/100 Selection signal · not a rating of the site

An open-source test suite measures whether agent-memory tools notice tampering, resist poisoned memories, and keep users separated.

Landing page captured for the 2026-09-22 issue.
For
AI agent and memory-tool maintainers
Worth noticing
It separates direct storage edits from poisoning through the normal memory-writing path.

Field notes

The project distinguishes attacks made directly against stored files from attacks delivered through the memory tool’s ordinary write path. Its homepage reports that three tested layers silently accepted all five direct edits, while a separate audit call exposed changes in one store. The front-door tests cover planted facts, stuffed entries, and hidden instructions, and the page says all four measured tools preserved user separation. Source code, papers, standards references, and reproducibility instructions are linked from the site.

Observed signals

Read the marks

Editorial observations of this landing page, not a rating.

OpenPublic substance visible
PrettyNotable craft visible
ProPolished or operationally mature
NicheUnusually specific use

One card from the complete issue

The Approximate Buildings of Mississauga

377,241 arrived 1,000 judged 981 catalogued Enter the complete issue
agentmemoryintegrity.org

Landing page observed 2026-09-22. The live site may have changed.