Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
Open accessThe DOI matches its Crossref record.
Abstract
Large Language Models (LLMs) have demonstrated remarkable prowess in generating contextually coherent responses, yet their fixed context windows pose fundamental challenges for maintaining consistency over prolonged multi-session dialogues. We introduce Mem0, a scalable memory-centric architecture that addresses this issue by dynamically extracting, consolidating, and retrieving salient information from ongoing conversations. Building on this foundation, we further propose an enhanced variant that leverages graph-based memory representations to capture complex relational structures among conversational elements. Through comprehensive evaluations on the LOCOMO benchmark, we systematically compare our approaches against six baseline categories. Empirical results demonstrate that our methods consistently outperform all existing memory systems across four question categories: single-hop, temporal, multi-hop, and open-domain. Notably, Mem0 achieves 26% relative improvements in the LLM-as-a-Judge metric over OpenAI, while Mem0 with graph memory achieves around 2% higher overall score than the base Mem0 configuration. Beyond accuracy gains, we also markedly reduce computational overhead compared to the full-context approach. In particular, Mem0 attains a 91% lower p95 latency and saves more than 90% token cost, thereby offering a compelling balance between advanced reasoning capabilities and practical deployment constraints. Our findings highlight the critical role of structured, persistent memory mechanisms for long-term conversational coherence, paving the way for more reliable and efficient LLM-driven AI agents. Code: https://mem0.ai/research.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Mem0 extracts, consolidates, and retrieves salient conversational information, including graph-based variants for relational memory [5].”
From Oracle Agent Memory as an Enterprise Memory Substrate for Long-Horizon AI Agents (2026) · cites this paper as [5]
In the citing paper
“At the same time, implementations remain fragmented across virtual-context managers, reflection buffers, memory-specific services, vector stores, graph layers, and framework abstractions [19, 23, 5, 21, 26, 11, 10].”
From Oracle Agent Memory as an Enterprise Memory Substrate for Long-Horizon AI Agents (2026) · cites this paper as [5]
In the citing paper
“Since many memoryenabled assistants retrieve memories using semantic similarity [Chhikara et al., 2025], the attacker can rewrite the adversarial memory goal to increase its similarity to likely future queries.”
From Hidden in Memory: Sleeper Memory Poisoning in LLM Agents (2026) · cites this paper as Chhikara et al., 2025
In the citing paper
“In external summarization systems, such as Mem0 [Chhikara et al., 2025], a separate process consolidates memories asynchronously, meaning defenses cannot be applied on-the-fly.”
From Hidden in Memory: Sleeper Memory Poisoning in LLM Agents (2026) · cites this paper as Chhikara et al., 2025
In the citing paper
“Our external manager adopts Mem0's open-source additive extraction prompt as a representative configuration; the evaluation does not depend on the Mem0 SDK or any specific product.”
From Hidden in Memory: Sleeper Memory Poisoning in LLM Agents (2026) · cites this paper as Chhikara et al., 2025
5 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cited by
Items 101–159 of 159
Hierarchical Long-Term Semantic Memory for LinkedIn's Hiring Agent
Xu, Z., Zhang, S., Poyraz, E., Li, Y., Jin, Y., Lu, X., Gu, X., Ramgopal, K., Bodigutla, P. K., & Wang, X. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3818432 · Cited by 3
FlowArk: Boosting Agentic Data-flow Analysis for Android Apps via Context-Aware Knowledge ReusePreprint
Zhang, Y., Wu, J., & Nan, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.11308
ViSAGE: Constructing Self-Correcting Memories for Long-Form Video Understanding
Zhao, X., Chen, E., Zhang, Y., Liu, C., Cheng, G., Wang, N., & Xu, Y. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3835852
Internet of Agents (IoA): Sensing, Communication, Decision-Making, and Execution
Wang, J., Ning, H., Ding, J., Zhu, T., & Daneshmand, M. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3729267 · Cited by 1
Lee, H., Oh, J., Ko, J., Kim, S., Park, J., Kim, H., Son, J., & Kang, P. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.01198
What Eviction Destroys: A Restore-Counterfactual Audit of Forgetting in Agent MemoryPreprint
Shen, C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.08279 · Cited by 1
Zhu, L., Lin, Y., Wang, Y., Liu, Y., Li, H. "., & Chen, Y. (2026) · International Workshop on Human-Centered Sensing, Modeling, and Intelligent Systems · doi:10.1145/3842436.3843817
MM-ContextFold: Context Folding for Multimodal Agentic Retrieval
Tian, Y., Liu, F., Zhang, J., Li, Z., Hu, Y., & Nie, L. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3836039
SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party DialoguePreprint
Zheng, H., Tang, T., Chen, Y., Wang, W., & Wu, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.26780
NLPG: Natural-Language Policy Gradients for Self-Evolving Language AgentsPreprint
Liu, X., Wei, W., Cao, J., Peng, D., Chen, H., Gui, Z., & Wu, H. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.33379
Learning to Retrieve Missing Evidence for Long-Term Memory QAPreprint
Deng, Y.-X., Zhang, Y., Liu, W., Xue, C., & Yang, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.37443
Org-Agent: Beyond Personal Assistants Towards Organizational AgentsPreprint
Zhuang, L., Zhang, Y., Hong, Z., Xiao, Y., & Huang, X. (2026) · arXiv (Cornell University)
Personalized State-Transition-Aware Memory for Clinical Agents
Haghifam, M., Rajabi, Z., Sun, Y., & Morato, C. (2026) · arXiv
StateWise: Diagnosing and Repairing Persistent Operational State Before Agent ActionsPreprint
Peng, Y., Feng, Z., Wu, T., Chen, J., Su, Y., Zhou, C., Du, T., & Ji, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.05241
RICO-Mem: Conflict-Aware Memory Management for Long-Term LLM Agents
Chen, S., Liu, Y., Hou, K., Cai, Y., Huang, J., & Jin, R. (2026) · International Conference on Computer Science and Blockchain (CCSB) · doi:10.1109/ccsb71176.2026.11716419
DOMR-Mem: Detecting, Repairing, and Preserving Long-Term LLM Memories
Chen, S., Liu, Y., Cai, Y., Hou, K., Huang, J., & Jin, R. (2026) · International Conference on Computer Science and Blockchain (CCSB) · doi:10.1109/ccsb71176.2026.11716445
Test-Time Adaptation of Reasoning Strategies with Bayesian Nonparametric MemoryPreprint
Ramji, K., Naseem, T., & Astudillo, R. F. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.06516
AIGuardian: A Parent-Regulated AI Chatbot Interface for Children
Bhullar, S. S., Khan, M., & Rani, K. M. S. (2026) · International Conference on Emerging Techniques in Computational Intelligence (ICETCI) · doi:10.1109/icetci71772.2026.11710429
Akbar, N. A., Turnip, A., & Caesarendra, W. (2026) · IEEE International Conference on Artificial Intelligence and Mechatronics Systems (AIMS) · doi:10.1109/aims71270.2026.11712645
Abeke, O., Nassr, R. M., & Mahmoud, H. (2026) · International Journal of Data Science and Analytics · doi:10.1007/s41060-026-01290-8
UniSkill: Learning Actor-Aligned Skill Proposals for an Evolving PolicyPreprint
Lu, Y., Liu, C., Yu, D., Xiang, H., Zhang, J., Xiao, Y., & Liang, R. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.10164 · Cited by 1
Use and Disuse: Intent-Structured Experience Consolidation for Memory and Learning in LLM AgentsPreprint
Zeng, X., Liu, B., Wang, X., Jin, Z., Li, Y., & Liu, Q. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.12124
Skill-V: Verifiable Self-Evolving Skill Library for Interactive AgentsPreprint
Ma, J., Qian, Z., Ma, Y., Liang, Z., Ji, J., Cai, Q., Chen, B., Jiang, P., & Sun, X. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.11781
Guo, H., Liu, F., Wang, Y., Qi, Y., Xiong, H., Sun, F., & Du, M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.11384 · Cited by 1
Temporal Evidence Forests for Long-Horizon Multi-Party Conversational MemoryPreprint
Guo, J., Tao, C., He, Y., Wang, Y., & Ma, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.12874
Seeing, Maintaining, and Learning: The Evolution of Multimodal Agent MemoryPreprint
Guo, M., Jiao, Q., Liu, X., Pang, J., Yang, R., Xu, N., Che, L., Xue, H., Wang, Z., Cai, X., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.19366 · Cited by 2
MemScope: Evolving Agent Memory Architectures through Localized Code RepairPreprint
Su, M., Guo, Y., Li, Z., Bai, L., Hou, Z., Jin, X., & Guo, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.21170 · Cited by 1
A Hierarchical Memory-Based Exploration Mechanism for Creative Language Model Agents
He, C., Bi, Z., Lou, J., Hu, Z., Xue, Z., Shen, Q., Liu, Z., & Zhao, K. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729301
CPGR-Mem: Cross-Platform Graph-based Routing Memory for Multimodal Intelligent Agents
Kong, J., & Zhao, Y. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11730075
HMem: A Hawkes Process Memory Framework for Long-Horizon Agents
Yan, Z., Wu, X., & Wei, J. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11728985
Agentic Memory Tagging: Scalable Yet Stable Indexing for Long-Term Memory
Zhu, S., Fan, M., Zhou, W., Ma, C., Liu, X., & Xiong, H. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11728438
Yang, Q., Yang, S., Xu, D., Wang, D., & Ding, M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.24359
Memories That Outlive Their Reasons: Dependency-Tethered Memory for Tool-Using LLM AgentsPreprint
Wang, Y., ju, J., Zhang, J., Wu, Z., Duan, Y., Sun, Z., Cai, T., & Zheng, M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.25123
Goswami, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.24030
What should AI forget? A design and taxonomy for negative space governance in AI memoryPreprint
Xu, E., Ding, K., Chang, T.-Y., Li, T., & Bashir, M. N. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.27607
Capability-Aware Dynamic Skill Selection for Memory-Augmented Generation
Qiao, Y., Wang, Y., Huang, C., Zhang, X., & Shang, S. (2026) · International Conference on Information Science and Technology · doi:10.1109/icist71072.2026.11727740
Transparent, Traceable, Deterministic: Agentic Memory via Knowledge Graphs
Gentile, A. L., An, S., & DeLuca, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-42029-9_16
Diagnosing Personalization Failures in Mobile GUI AgentsPreprint
Lin, Z., Xu, D., Li, J., Pan, S., Feng, J., Sun, Y., Li, J., Liu, L., & Yao, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.30573
Wang, Y., Zeng, Z., Zhang, J., Duan, Y., Zheng, M., & Cai, T. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.31107
Seamless: Self-Maintaining Knowledge Graph Memory for Retrieval-Augmented Language Models
Smirnov, N. (2026) · IEEE Access · doi:10.1109/access.2026.3747787
Adaptive Memory Index Evolution for AgentsPreprint
Hu, Y., Su, T., Sun, Y., Ma, S., Tan, Q., & Zhao, L. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.34977 · Cited by 1
Learning to remember: advances in memory mechanisms for large language models
Han, C., Yu, H., Wu, M., Zhang, D., & Luo, J. (2026) · Vicinagearth. · doi:10.48550/arxiv.2610.35089
Agent Memory as Recommendation: Recommender-System Design for Long-Term Memory of LLM AgentsPreprint
Zhang, X., & Sun, W. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.34673
EvolveMAS: A Unified Self-Evolution Framework for Decentralized Multi-Agent SystemsPreprint
Wu, Y., Ma, Q., Xu, B., Zhang, D., Bai, L., Wang, B., Li, J., Lv, Z., Yuan, S., Wang, P., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.34450
When Retrieval Is Not Enough: Obsolete Facts in Agent MemoryPreprint
Poikarayil, O. B., Babu, T. B., Nahhas, A., Mehta, H. D., Baktash, J. A., Luca, E. W. D., & Turowski, K. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.36308
Liu, J., Liu, T., & Zhang, C. (2026) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2026.113770
Liu, X., Li, X., Zeng, Q., Yang, M., & Xiu, S. (2026) · Abu Dhabi International Petroleum Exhibition & Conference (ADIPEC) · doi:10.2118/235328-ms
TMemAgent: Transferable Memory for Cross-Domain User Behaviour Simulation
Ahmed, M. F., He, J., Ma, C., & Chan, J. (2026) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3799682.3840738
Immune Memory: Contradiction Filtering at Write Time for Long-Term LLM AgentsPreprint
Tishkov, V. (2026) · doi:10.24108/preprints-3116872
MemDTG: Dynamic Temporal Memory Graphs for Evidence-Admissible Agent Memory
Deng, Y., Qin, H., Gao, T., Zeng, G., & Li, R.-H. (2026) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3799682.3841052
H-Mem: Hawkes-driven Adaptive Forgetting for Long-Horizon Agent Memory
Wu, X., Qin, H., Zeng, G., Li, R.-H., & Zhao, K. (2026) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3799682.3840962
From Interaction Traces to Reusable Experiences for LLM Agents
Fettache, D. (2026) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3799682.3840216
MemShift: Separating Detection from Repair in LLM-Derived Personal MemoryPreprint
Xu, Z., Zhang, H., Dong, Y., Onizuka, M., & Xiao, C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2611.02338
Memorix: Managing Memory Selections for AI AgentsPreprint
Zhang, J., Song, X., Du, D., Feng, E.-H., & Xia, Y.-B. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2611.00060
Nguyen, N., Phan, C. N. L., Le, T., Truong, K., Thị, N., Pham, Q. V., & Quan, T. T. (2026) · Communications in computer and information science · doi:10.1007/978-981-92-7411-6_33
Nannapaneni, S. K., & Nannapaneni, J. (2026) · doi:10.1109/icact70625.2026.11748725
Can Coding Agents Sustain Continual Evolution without Forgetting?Preprint
Zhao, S., Zhang, Y., & Li, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2611.03219 · Cited by 1
One Assistant, Many Memories: Benchmarking Real-World Group Assistance When Recall Is Not EnoughPreprint
Hu, Z., Zhang, L., Zhao, Q., Zhu, Q., Hua, Y., Liang, D., Si, J., Zhao, X., He, Y., Chen, Z., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2611.04867
Twists and Turns: A Graph-Based Benchmark and Framework for Long-Term Memory in Exploration TasksPreprint
Dai, C., Shen, Y., Song, Z., Liao, J., Hu, J., & Chen, X. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2611.06414
Metadata
- Authors
- Chhikara, P., Khant, D., Aryan, S., Singh, T., & Yadav, D.
- Affiliations
- Mem0.ai, research@mem0.ai
- Venue
- Frontiers in Artificial Intelligence and Applications
- Publisher
- IOS Press
- Published
- 2025-10-21
- ISSN
- 0922-6389 (ISSN-L)
- 1879-8314
- OpenAlex
- W4415428439
- Cited by
- 69
- References
- 0
- Citations by year
- 2026: 62 · 2025: 7
- FWCI
- 138.55
- Type
- book chapter
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Frontiers in artificial intelligence and applications (publishedVersion, cc-by-nc)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- long-term memory, conversational AI agents, large language models, memory-centric architecture, LLM-as-a-judge, computational efficiency, persistent memory
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.