getzep/zep
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.
Key facts
| Category | Memory system |
|---|---|
| License | Apache-2.0 |
| Maintainer | Zep |
| Compatible agents | generic |
| File patterns | |
| Triggering | manual-reference |
| GitHub metrics | 4,732 stars · 637 forks · 15 open issues (fetched 2026-07-07) |
| Last commit | 2026-07-06 |
| Created | 2023-04-29 |
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
pip install zep-cloud # or self-host per docsAlternatives in this category
A universal memory layer for AI agents: extraction, storage, and retrieval of user and session memories with SDKs across the major agent…
A platform for stateful agents with self-editing memory, descended from the MemGPT research line: agents manage their own memory blocks…
Local-first agent memory over plain Markdown files with an MCP interface: knowledge persists as human-readable notes the agent reads and…
Embed this badge
Maintainers of scored entries can embed their live badge; it updates when the score does and links back to this page.
[](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.