Common questions
Won't Claude or Codex just build this?
Anthropic and OpenAI build models. Lore builds what teams do with them. Claude doesn't know your org structure, your access controls, who's on what team, or what Marcus tried last March. That's a permanently different product — and the value compounds the longer your team uses it. A year from now you'll have a year of captured reasoning. You can't turn on a feature and get that back.
How is this different from Claude's built-in memory?
Claude memory is per-person and per-context. It helps you individually across sessions. Lore works across your whole team — capturing what every engineer figures out and making it searchable by anyone. When your session closes, Claude memory stays with you. Lore stays with the org.
What about just saving sessions to a shared doc or repo?
Docs capture what you decided. Lore captures why — what you tried, what failed, what you almost did instead. Nobody writes that in a doc, and nobody reads the docs that do exist. Lore captures it automatically from where the actual work is happening.
Does Lore share everything my team does in Claude and Codex?
No. You control what's shared. Private sessions stay private. Lore only surfaces what you choose to make visible to the team.
What teams is Lore built for?
Teams where engineers are spending significant time in Claude Code or Codex as their primary work environment. If your team is doing 4 or more hours a day in AI sessions, the knowledge-isolation problem is real and getting worse.