History

JabberELF 7a450ca5ce fix(memory): resolve dim=1 float32/float64 blob ambiguity When hrr_dim=1 the prefixed float32 blob (4+4=8 bytes) collides in size with a raw float64 blob (1×8=8 bytes), making the format discriminator in bytes_to_phases ambiguous — a legacy blob starting with HRR1 would be misread as a prefixed float32 vector. - phases_to_bytes now accepts an optional dim and falls back to writing raw float64 when the two blob sizes are equal. - bytes_to_phases prefers the legacy float64 interpretation when sizes collide and dim is provided, since phases_to_bytes never writes a prefixed float32 blob at dim=1. - Three regression tests cover dim=1 write, round-trip, and the legacy-prefix collision case. Addresses hermes-sweeper review on PR #30499.		2026-08-02 22:33:13 +05:30
..
README.md	…
__init__.py	…
holographic.py	fix(memory): resolve dim=1 float32/float64 blob ambiguity	2026-08-02 22:33:13 +05:30
plugin.yaml	…
retrieval.py	perf(memory): store holographic vectors as float32	2026-08-02 22:33:13 +05:30
store.py	perf(memory): store holographic vectors as float32	2026-08-02 22:33:13 +05:30

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)