Documentation

Memory that answers for itself

OMEM is a memory layer for AI agents that answers for itself. You store beliefs; OMEM tracks who claimed what, when, on what basis, and whether anything contradicts it, so you can always answer why your agent believes something.

You don't need to learn the underlying memory model to be productive. The SDK speaks in remember, believes, why, and history. The rigorous machinery of provenance graphs, belief intervals, and contradiction states runs underneath.

Install

1pip install omem

What you get

PROVENANCE

Every belief traces to the events and derivations that produced it.

TIME

Query what your agent knew at any point in time, deterministically.

CONTRADICTION

Conflicting claims resolve to a state, never a silent overwrite.

HISTORY

Append-only. Revisions and retractions are recorded and auditable.