{"work":{"id":"515c933e-12ae-439d-a7ff-c07fee482dfb","openalex_id":null,"doi":null,"arxiv_id":"2501.13956","raw_key":null,"title":"Zep: A Temporal Knowledge Graph Architecture for Agent Memory","authors":null,"authors_text":"Preston Rasmussen, Pavlo Paliychuk, Travis Beauvais, Jack Ryan, Daniel Chalef","year":2025,"venue":"cs.CL","abstract":"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.","external_url":"https://arxiv.org/abs/2501.13956","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-18T01:00:34.613952+00:00","pith_arxiv_id":"2501.13956","created_at":"2026-05-10T06:16:20.807808+00:00","updated_at":"2026-05-18T01:00:34.613952+00:00","title_quality_ok":true,"display_title":"Zep: A Temporal Knowledge Graph Architecture for Agent Memory","render_title":"Zep: A Temporal Knowledge Graph Architecture for Agent Memory"},"hub":{"state":{"work_id":"515c933e-12ae-439d-a7ff-c07fee482dfb","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":52,"external_cited_by_count":null,"distinct_field_count":8,"first_pith_cited_at":"2025-07-04T17:21:46+00:00","last_pith_cited_at":"2026-05-14T05:38:24+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-05-18T09:50:33.796271+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":10},{"context_role":"baseline","n":2}],"polarity_counts":[{"context_polarity":"background","n":10},{"context_polarity":"baseline","n":2}],"runs":{"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-14T17:48:52.866423+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":"Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory","work_id":"a5aed26c-a248-48b6-a59e-f7693fcb180a","shared_citers":33},{"title":"MemGPT: Towards LLMs as Operating Systems","work_id":"2698f5ad-c84c-40ca-b839-0912dae10ba2","shared_citers":23},{"title":"A-MEM: Agentic Memory for LLM Agents","work_id":"3b98feb2-fdb1-479a-bbe4-2c298a4592e2","shared_citers":22},{"title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","work_id":"588618d7-fd41-4053-b34d-a981f8793039","shared_citers":20},{"title":"LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory","work_id":"9074870f-aee7-4103-b167-ac6473a8a9b3","shared_citers":12},{"title":"Memory in the Age of AI Agents","work_id":"1ff75a14-302e-4906-aa86-1f96fbcf12ff","shared_citers":11},{"title":"Memos: A memory os for ai system","work_id":"e686f058-6c5c-4484-a88e-26d945657ed3","shared_citers":10},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":10},{"title":"Evaluating Very Long-Term Conversational Memory of LLM Agents","work_id":"2d8c9fb7-9ace-4925-8fe1-f4e44625d04c","shared_citers":8},{"title":"From human memory to ai memory: A survey on memory mechanisms in the era of llms.arXiv preprint arXiv:2504.15965","work_id":"56f08885-28c9-4956-88e1-91190c6ca650","shared_citers":8},{"title":"From rag to memory: Non-parametric continual learning for large language models","work_id":"f768fbda-cd1e-4a8e-b67c-040f4242fe93","shared_citers":8},{"title":"Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning","work_id":"2a070440-2167-4398-be97-c2d4c3ee3541","shared_citers":8},{"title":"Evaluating memory in llm agents via incremental multi-turn interactions","work_id":"df5096c3-e738-472b-953c-fb510ee9e68d","shared_citers":7},{"title":"Retrieval-Augmented Generation for Large Language Models: A Survey","work_id":"b80d2790-6cd9-4c87-b3c4-de404f99a80e","shared_citers":7},{"title":"A survey on the memory mechanism of large language model based agents","work_id":"86a3cea2-e600-466a-bf9e-6e737a41ed6a","shared_citers":6},{"title":"MEM1: learning to synergize memory and reasoning for efficient long-horizon agents.CoRR, abs/2506.15841","work_id":"43cfa793-fb98-4501-8224-4dfb9e56285c","shared_citers":6},{"title":"Memos: An operating system for memory-augmented generation (mag) in large language models","work_id":"62f802d2-2c22-4140-9b3d-b8b7220f772e","shared_citers":6},{"title":"Mirix: Multi-agent memory system for llm-based agents","work_id":"bcb99885-6f76-4bd6-b442-e5f455bb6447","shared_citers":6},{"title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","work_id":"ffe0d207-86cf-4742-a100-e988ac8b9676","shared_citers":6},{"title":"What Deserves Memory: Adaptive Memory Distillation for LLM Agents","work_id":"8025a606-5218-4c5a-b99f-83049e7feac5","shared_citers":6},{"title":"arXiv preprint arXiv:2506.07398 , year=","work_id":"e5c4ec9c-3e43-42d1-a3d7-0deef9c44093","shared_citers":5},{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":5},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":5},{"title":"Halumem: Evaluating hallucinations in memory systems of agents","work_id":"7ca25b51-b6cf-4bc9-b1cf-e521d7651cf1","shared_citers":5}],"time_series":[{"n":1,"year":2025},{"n":40,"year":2026}],"dependency_candidates":[]},"error":null,"updated_at":"2026-05-14T17:49:15.031614+00:00"},"identity_refresh":{"job_type":"identity_refresh","status":"succeeded","result":{"items":[{"title":"Qwen3 Technical Report","outcome":"unchanged","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","resolver":"local_arxiv","confidence":0.98,"old_work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e"}],"counts":{"fixed":0,"merged":0,"unchanged":1,"quarantined":0,"needs_external_resolution":0},"errors":[],"attempted":1},"error":null,"updated_at":"2026-05-14T17:49:11.686182+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"Zep: A Temporal Knowledge Graph Architecture for Agent Memory","claims":[{"claim_text":"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 addresse","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Zep: A Temporal Knowledge Graph Architecture for Agent Memory because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-14T17:48:36.551566+00:00"}},"summary":{"title":"Zep: A Temporal Knowledge Graph Architecture for Agent Memory","claims":[{"claim_text":"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 addresse","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Zep: A Temporal Knowledge Graph Architecture for Agent Memory because it crossed a citation-hub threshold.","role_counts":[]},"graph":{"co_cited":[{"title":"Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory","work_id":"a5aed26c-a248-48b6-a59e-f7693fcb180a","shared_citers":33},{"title":"MemGPT: Towards LLMs as Operating Systems","work_id":"2698f5ad-c84c-40ca-b839-0912dae10ba2","shared_citers":23},{"title":"A-MEM: Agentic Memory for LLM Agents","work_id":"3b98feb2-fdb1-479a-bbe4-2c298a4592e2","shared_citers":22},{"title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","work_id":"588618d7-fd41-4053-b34d-a981f8793039","shared_citers":20},{"title":"LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory","work_id":"9074870f-aee7-4103-b167-ac6473a8a9b3","shared_citers":12},{"title":"Memory in the Age of AI Agents","work_id":"1ff75a14-302e-4906-aa86-1f96fbcf12ff","shared_citers":11},{"title":"Memos: A memory os for ai system","work_id":"e686f058-6c5c-4484-a88e-26d945657ed3","shared_citers":10},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":10},{"title":"Evaluating Very Long-Term Conversational Memory of LLM Agents","work_id":"2d8c9fb7-9ace-4925-8fe1-f4e44625d04c","shared_citers":8},{"title":"From human memory to ai memory: A survey on memory mechanisms in the era of llms.arXiv preprint arXiv:2504.15965","work_id":"56f08885-28c9-4956-88e1-91190c6ca650","shared_citers":8},{"title":"From rag to memory: Non-parametric continual learning for large language models","work_id":"f768fbda-cd1e-4a8e-b67c-040f4242fe93","shared_citers":8},{"title":"Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning","work_id":"2a070440-2167-4398-be97-c2d4c3ee3541","shared_citers":8},{"title":"Evaluating memory in llm agents via incremental multi-turn interactions","work_id":"df5096c3-e738-472b-953c-fb510ee9e68d","shared_citers":7},{"title":"Retrieval-Augmented Generation for Large Language Models: A Survey","work_id":"b80d2790-6cd9-4c87-b3c4-de404f99a80e","shared_citers":7},{"title":"A survey on the memory mechanism of large language model based agents","work_id":"86a3cea2-e600-466a-bf9e-6e737a41ed6a","shared_citers":6},{"title":"MEM1: learning to synergize memory and reasoning for efficient long-horizon agents.CoRR, abs/2506.15841","work_id":"43cfa793-fb98-4501-8224-4dfb9e56285c","shared_citers":6},{"title":"Memos: An operating system for memory-augmented generation (mag) in large language models","work_id":"62f802d2-2c22-4140-9b3d-b8b7220f772e","shared_citers":6},{"title":"Mirix: Multi-agent memory system for llm-based agents","work_id":"bcb99885-6f76-4bd6-b442-e5f455bb6447","shared_citers":6},{"title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","work_id":"ffe0d207-86cf-4742-a100-e988ac8b9676","shared_citers":6},{"title":"What Deserves Memory: Adaptive Memory Distillation for LLM Agents","work_id":"8025a606-5218-4c5a-b99f-83049e7feac5","shared_citers":6},{"title":"arXiv preprint arXiv:2506.07398 , year=","work_id":"e5c4ec9c-3e43-42d1-a3d7-0deef9c44093","shared_citers":5},{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":5},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":5},{"title":"Halumem: Evaluating hallucinations in memory systems of agents","work_id":"7ca25b51-b6cf-4bc9-b1cf-e521d7651cf1","shared_citers":5}],"time_series":[{"n":1,"year":2025},{"n":40,"year":2026}],"dependency_candidates":[]},"authors":[]}}