By Vero SecurityBuilt and funded by Vero Security, the AI Security Engineering platform.Read the charter

Reviewing auto memory files per project

Claude Code auto memory stores a MEMORY.md index and topic files under ~/.claude/projects, loads the first 200 lines or 25KB each session, and keeps them outside the transcript cleanup sweep. Read these files after suspicious sessions, and note that autoMemoryEnabled can turn the feature off per project.

Read in this order

  1. OfficialAuto memory (Claude Code docs)Storage path, load limits, autoMemoryEnabled and autoMemoryDirectory settings.

Save your progress

We email you a sign-in link. No password.

By signing in you agree to the terms. The privacy policy explains how we use your details.

Join the AI security engineering community

Free. Roadmap updates, chapters near you, and first word when credentials open.

We’ll email you community updates. Unsubscribe anytime. By sending this you agree to the terms. The privacy policy explains how we use your details.