Home / Compare / Zep / Graphiti

Lians vs Zep / Graphiti.

Zep / Graphiti is the temporal knowledge graph, scored on the same five invariants we score ourselves. Credit where it's strong, receipts where it isn't.

Credit first

Where Zep / Graphiti is genuinely strong.

Zep is strong at conversational knowledge graphs: bitemporal edges, contradiction invalidation, and temporal filtering.

Regulated-memory eval · last run 2026-07-04

The five invariants.

Regulated invariantLiansZep / Graphiti
Stale revision suppressedpasspartial
Point-in-time (as-of) recallpasspartial
Provable erasure (crypto-shred + cert)passpartial
Lookahead / backtest guardpassabsent
Audit-state snapshot at Tpasspartial
Score (pass = 1, partial = ½)5.0 / 52.0 / 5

Both columns executed live: Graphiti OSS in its default documented config. Its contradiction invalidation genuinely works - but default search still returns invalidated edges unless the caller filters them. Evidence in the methodology doc ↗.

Where the lanes diverge

Different jobs, different guarantees.

The gap is proof: no as-of recall primitive, deletion certificate, lookahead guard, or first-class snapshot API. Lians also adds database-level isolation and write admission.

The honest recommendation

Which should you pick?

Choose Zep for graph-shaped memory. Choose Lians for deterministic time, audit, and proof-producing erasure.

Full comparison ↗

Open methodology

Zep and Graphiti have a public right of reply.

We asked the Graphiti maintainers to review the configuration, evidence, and scoring in public. If a default behavior, documented capability, or result is wrong, we will rerun the adapter and correct this page.

Read or respond to the public fact-check request ↗

Bring the numbers to your compliance officer.

Get an API key →