# NousResearch/hermes-agent · Holographic memory auto-extract fact derivation fix

## Open now

- 1 issue, 3 PRs open on GitHub.
- #22907: holographic memory \`auto_extract\` saves raw user messages verbatim instead of extracting preferences
- PR #22959: fix(memory): derive holographic auto-extracted facts
- PR #39667: fix(memory): extract clean declarative facts instead of raw messages in holographic auto_extract (#22907)
- PR #100744: fix(holographic): store the captured span, not the whole user message

These issues and pull requests concern a bug where holographic memory's auto-extract feature saves raw user messages verbatim rather than deriving clean declarative facts or preferences. Multiple fix attempts address extracting structured facts instead of storing unprocessed message content.

## TL;DR

- 5 member(s): 1 open issue(s), 0 closed issue(s), 3 open PR(s), 0 merged PR(s), 1 PR(s) closed without merging.
- No fix has been merged to main; one or more PRs were attempted (see below).
- **Recommended:** review the prior/competing PR(s) below. A fix was attempted but not merged; your case may extend or revive that work.

## Maintainer resolution verdict

- Internal-tracker verdict over this cluster's issue members: `unresolved`. This is distinct from the fix status above. Weigh it yourself.

## How this cluster was grouped

- Link evidence (`STRUCTURAL_SPANNING`): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.
- Pairwise link density `0.40`: the share of member pairs that carry a link, counting a structural link in full and a relevance-only link at 0.36. `1.00` means every pair is linked.

## Open related issues

- #22907: holographic memory \`auto_extract\` saves raw user messages verbatim instead of extracting preferences

## Prior & competing PRs

- **#22959: fix(memory): derive holographic auto-extracted facts**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`
  - files: `plugins/memory/holographic/__init__.py`, `tests/plugins/memory/test_holographic_auto_extract.py`
- **#39667: fix(memory): extract clean declarative facts instead of raw messages in holographic auto_extract (#22907)**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`
  - files: `plugins/memory/holographic/__init__.py`, `tests/plugins/memory/test_auto_extract.py`
- **#84312: fix(memory): safely derive holographic auto-extracted facts**. closed without merge
  - maintainer direction: category `implemented_elsewhere`; implication `superseded`
- **#100744: fix(holographic): store the captured span, not the whole user message**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`
  - files: `plugins/memory/holographic/__init__.py`, `tests/plugins/memory/test_holographic_auto_extract.py`

## Fix status

- No merged fix on record.
- Subsystem: `agent`