Zep: A Temporal Knowledge Graph Architecture for Agent Memory

Papers with Code Trending Papers
agent-memory knowledge-graph temporal-reasoning rag llm-agents

Summary

This paper introduces Zep, a temporal knowledge graph architecture for agent memory that outperforms MemGPT in benchmarks like DMR and LongMemEval. It highlights Zep's ability to handle dynamic knowledge integration and temporal reasoning for enterprise use cases.

We introduce Zep, a novel memory layer service for AI agents that outperforms the current state-of-the-art system, MemGPT, in the Deep Memory Retrieval (DMR) benchmark. Additionally, Zep excels in more comprehensive and challenging evaluations than DMR that better reflect real-world enterprise use cases. While existing retrieval-augmented generation (RAG) frameworks for large language model (LLM)-based agents are limited to static document retrieval, enterprise applications demand dynamic knowledge integration from diverse sources including ongoing conversations and business data. Zep addresses this fundamental limitation through its core component Graphiti -- a temporally-aware knowledge graph engine that dynamically synthesizes both unstructured conversational data and structured business data while maintaining historical relationships. In the DMR benchmark, which the MemGPT team established as their primary evaluation metric, Zep demonstrates superior performance (94.8% vs 93.4%). Beyond DMR, Zep's capabilities are further validated through the more challenging LongMemEval benchmark, which better reflects enterprise use cases through complex temporal reasoning tasks. In this evaluation, Zep achieves substantial results with accuracy improvements of up to 18.5% while simultaneously reducing response latency by 90% compared to baseline implementations. These results are particularly pronounced in enterprise-critical tasks such as cross-session information synthesis and long-term context maintenance, demonstrating Zep's effectiveness for deployment in real-world applications.
Original Article
View Cached Full Text

Cached at: 05/08/26, 08:54 AM

Paper page - Zep: A Temporal Knowledge Graph Architecture for Agent Memory

Source: https://huggingface.co/papers/2501.13956 Published on Jan 20, 2025

Abstract

Zep, a memory layer service, outperforms MemGPT in the DMR benchmark and LongMemEval by excelling in dynamic knowledge integration and temporal reasoning, critical for enterprise use cases.

We introduce Zep, a novelmemory layer servicefor AI agents that outperforms the current state-of-the-art system,MemGPT, in theDeep Memory Retrieval (DMR)benchmark. Additionally, Zep excels in more comprehensive and challenging evaluations than DMR that better reflect real-world enterprise use cases. While existingretrieval-augmented generation (RAG)frameworks for large language model (LLM)-based agents are limited to static document retrieval, enterprise applications demand dynamic knowledge integration from diverse sources including ongoing conversations and business data. Zep addresses this fundamental limitation through its core componentGraphiti-- atemporally-awareknowledge graph enginethat dynamically synthesizes bothunstructured conversational dataandstructured business datawhile maintaining historical relationships. In the DMR benchmark, which theMemGPTteam established as their primary evaluation metric, Zep demonstrates superior performance (94.8% vs 93.4%). Beyond DMR, Zep’s capabilities are further validated through the more challengingLongMemEvalbenchmark, which better reflects enterprise use cases through complex temporal reasoning tasks. In this evaluation, Zep achieves substantial results with accuracy improvements of up to 18.5% while simultaneously reducing response latency by 90% compared to baseline implementations. These results are particularly pronounced in enterprise-critical tasks such ascross-session information synthesisandlong-term context maintenance, demonstrating Zep’s effectiveness for deployment in real-world applications.

View arXiv pageView PDFGitHub25.8kautoAdd to collection

Get this paper in your agent:

hf papers read 2501\.13956

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2501.13956 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2501.13956 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2501.13956 in a Space README.md to link it from this page.

Collections including this paper9

Browse 9 collections that include this paper

Similar Articles