History

teknium1 638d2e7bfc fix(memory/holographic): apply FTS5 sanitizer to search_facts sibling The store-level search_facts() shared the same raw-MATCH bug class as _fts_candidates (FTS5 AND-joins tokens, zeroing prose recall). Route it through FactRetriever._sanitize_fts_query via a lazy import to keep the store->retrieval layering acyclic. Also add cyb3rwr3n to release AUTHOR_MAP.		2026-06-30 15:55:11 -07:00
..
__init__.py	fix(memory/holographic): close DB connection on shutdown instead of leaking to GC (#54133 )	2026-06-28 02:41:52 -07:00
holographic.py
plugin.yaml
README.md
retrieval.py	fix(memory/holographic): sanitize FTS5 queries for natural-language recall	2026-06-30 15:55:11 -07:00
store.py	fix(memory/holographic): apply FTS5 sanitizer to search_facts sibling	2026-06-30 15:55:11 -07:00

Holographic Memory Provider

Local SQLite fact store with FTS5 search, trust scoring, entity resolution, and HRR-based compositional retrieval.

Requirements

None — uses SQLite (always available). NumPy optional for HRR algebra.

hermes memory setup    # select "holographic"

Or manually:

hermes config set memory.provider holographic

Config in config.yaml under plugins.hermes-memory-store:

Key	Default	Description
`db_path`	`$HERMES_HOME/memory_store.db`	SQLite database path
`auto_extract`	`false`	Auto-extract facts at session end
`default_trust`	`0.5`	Default trust score for new facts
`hrr_dim`	`1024`	HRR vector dimensions

Tool	Description
`fact_store`	9 actions: add, search, probe, related, reason, contradict, update, remove, list
`fact_feedback`	Rate facts as helpful/unhelpful (trains trust scores)