Source Intelligence

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 v2.1.76 Home All releases olderv2.1.75 v2.1.77newer
Claude Code v2.1.76

Automatic Memory Extraction [In Development]

Feature flag
tengu_passport_quail Off in both readings

The flag server returned off for the account this site reads and for the anonymous baseline. A reading of off cannot rule out a rollout these two readings sit outside of.

This account: off · anonymous baseline: off · compiled default in v2.1.76: no gate table built for this version

These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.

tengu_bramble_lintel Not enough to say

Nothing here resolved what this flag was doing on this version, so nothing here should be read as on or off.

This account: no value returned · anonymous baseline: no value returned · compiled default in v2.1.76: no gate table built for this version

These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.

Read once, for one account on one subscription tier, against v2.1.76. It isn't a statement about your account. What a flag value here can and cannot tell you

What

A background agent that automatically extracts and saves memories from conversations, running alongside the main conversation without user intervention.

Status

Feature-flagged behind tengu_passport_quail (default: false)

Details
  • After each turn, a background agent analyzes recent messages and saves relevant information to memory files
  • Uses the tengu_bramble_lintel flag to control how many turns to accumulate before running (default: 1)
  • Supports both private (user-only) and team (shared) memory scopes
  • Team memory format controlled by tengu_swinburne_dune flag (alternative two-step format)
  • Tracks which files the conversation has already written to, skipping extraction if the user manually saved memories
  • Coalesces rapid extractions: if one is already running, subsequent requests are stashed for a trailing run
  • Sends notification: "Saved N memor(y|ies)" when memories are written
  • Memory extraction agent is restricted to only Write, Read, and Edit tools within the memory directory
  • System prompt: "A background agent automatically extracts and saves memories from this conversation. If the user asks you to remember or forget something, acknowledge it — the save happens automatically."
Evidence

Memory extraction system (search for "tengu_passport_quail", "[extractMemories]", "extract_memories")

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

See this entry in the whole of v2.1.76 →