Claude Memory is a new feature for team and enterprise users that remembers conversations to maintain context across projects. It creates separate, project-based memories and gives users full control to view, edit, or disable what Claude remembers.
Replies
Best
one thing I keep thinking about with team memory: the real win is when the rules and skills a teammate figured out last sprint become automatic for the next person who picks up that repo. memory-of-facts is necessary, but the harder layer is portable skills — the "here's how we write tests, here's how we do code review, here's our CLAUDE.md" stuff. without that, persistent memory just gives you longer context, not shared institutional knowledge. building at the skills layer over at tokrepo (open source registry approach) because I think it complements this nicely — memory for facts, skills for conventions.
Replies
one thing I keep thinking about with team memory: the real win is when the rules and skills a teammate figured out last sprint become automatic for the next person who picks up that repo. memory-of-facts is necessary, but the harder layer is portable skills — the "here's how we write tests, here's how we do code review, here's our CLAUDE.md" stuff. without that, persistent memory just gives you longer context, not shared institutional knowledge. building at the skills layer over at tokrepo (open source registry approach) because I think it complements this nicely — memory for facts, skills for conventions.