◈AI Codex
Foundation Models & LLMs◆ Claude

Memory

Also: Claude Memory, persistent memory

Memory is Claude remembering things about you across conversations and tasks: your role, your preferences, the projects you are working on. You don't have to re-explain yourself every time. You can read, edit and delete what it remembers under Settings > Memory, and sensitive topics such as health are left out unless you turn them on. On Team and Enterprise, admins decide whether memory is available. Projects also keep their own memory, separate from your personal one.

◎

In practice

You tell Claude your name and preferred working style at the start of a session. With Memory enabled, Claude stores that — so next week, it already knows. Without it, every session starts blank. Claude's Memory feature is what makes the assistant feel like it knows you rather than meeting you for the first time every conversation.

Related concepts

Where Memory shows up

1 article