Follow Discord

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

← All of v2.1.80 Home All releases ←olderv2.1.79 v2.1.81newer→

Claude Code v2.1.80 19 Mar 2026

Improved Agent Memory Scope Labels

The agent memory enablement prompt now uses clearer scope labels: "User scope (~/.claude/agent-memory/)" and "Project scope (.claude/agent-memory/)" instead of the previous generic "Enable" labels, making it easier to understand where memories will be stored.

Evidence

Updated scope labels (search for "User scope (~/.claude/agent-memory/) (Recommended)" and "Project scope (.claude/agent-memory/) (Recommended)")

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

See this entry in the whole of v2.1.80 →