getzep/zep

A-Tier scored 2026-07-07 metrics 2026-07-07

A temporal knowledge-graph memory layer for agents: facts extracted from conversations with validity intervals, so recall can answer what was true when. Agentiquette scores it 74/100 (A-tier), methodology v1.0, scored 2026-07-07.

74/100 A-Tier
scored 2026-07-07 · methodology v1.0 · how we score
Reliability7225%
Skill Leverage7420%
Documentation7815%
Maintenance8410%
Safety / Governance7010%
Evaluation Readiness6810%
Composability745%
Adoption (capped)665%

Key facts

CategoryMemory system
LicenseApache-2.0
MaintainerZep
Compatible agentsgeneric
File patterns
Triggeringmanual-reference
GitHub metrics4,732 stars · 637 forks · 15 open issues (fetched 2026-07-07)
Last commit2026-07-06
Created2023-04-29

Editorial analysis

The most direct commercial answer to the freshness axis of our Memory Safety Model: facts carry validity intervals, so a changed address supersedes rather than coexists with the old one. That design choice alone earns the entry. The open-core boundary is the thing to diligence.

Risks

OSS repo increasingly orients toward the hosted product; check feature parity before committing to self-host.

Evidence notes: Safety/freshness: temporal validity on facts is native, unique in the class. Maintenance: active. Adoption: modest OSS traction, log-capped; the hosted product's traction is not measurable here.

Install and first run

install · not yet run by us
pip install zep-cloud  # or self-host per docs

Alternatives in this category

Compare with mem0 · Compare with letta

Embed this badge

Maintainers of scored entries can embed their live badge; it updates when the score does and links back to this page.

Agentiquette: A tier, 74/100

README.md
[![Agentiquette](https://agentiquette.com/badge/zep.svg)](https://agentiquette.com/index/repos/zep)

Frequently asked questions

Is getzep/zep good?

getzep/zep scores 74/100 (A-tier) on Agentiquette's methodology v1.0, scored 2026-07-07. Strengths and weaknesses are in the editorial analysis; the score is explained dimension by dimension in the scorecard.

What is getzep/zep for?

A temporal knowledge-graph memory layer for agents: facts extracted from conversations with validity intervals, so recall can answer what was true when.

Is getzep/zep maintained?

Last commit 2026-07-06, 15 open issues at fetch time (2026-07-07). Maintenance is scored at 84 of 100.

Maintainer of getzep/zep? Claim this listing and suggest corrections.