hermes-agent/plugins/memory/holographic
teknium1 a801046669 fix(memory): resolve() the shared-connection registry key; symlink test
Follow-ups for salvaged PR #43819: the registry key was
str(Path(db_path).expanduser()) — a symlinked or relative path to the
same DB file got its own connection, silently reintroducing the exact
multi-writer contention the registry prevents. Key on Path.resolve()
(OSError-tolerant fallback). Adds a symlink regression test and the
AUTHOR_MAP entry for adambiggs.
2026-07-09 18:17:40 -07:00
..
__init__.py fix(memory): share one SQLite connection per holographic store database 2026-07-09 18:17:40 -07:00
holographic.py feat(memory): pluggable memory provider interface with profile isolation, review fixes, and honcho CLI restoration (#4623) 2026-04-02 15:33:51 -07:00
plugin.yaml feat(memory): pluggable memory provider interface with profile isolation, review fixes, and honcho CLI restoration (#4623) 2026-04-02 15:33:51 -07:00
README.md feat(memory): pluggable memory provider interface with profile isolation, review fixes, and honcho CLI restoration (#4623) 2026-04-02 15:33:51 -07:00
retrieval.py fix(memory/holographic): sanitize FTS5 queries for natural-language recall 2026-06-30 15:55:11 -07:00
store.py fix(memory): resolve() the shared-connection registry key; symlink test 2026-07-09 18:17:40 -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.

Setup

hermes memory setup    # select "holographic"

Or manually:

hermes config set memory.provider holographic

Config

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

Tools

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)