Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory

By P. Chhikara, Dev Khant, Saket Aryan, Taranjeet Singh, Deshraj Yadav. European Conference on Artificial Intelligence, 2025

478 citations recorded by the source corpus.

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 LOCOMO benchmark, we systematically compare our approaches against six baseline categories: (i) established memory-augmented systems, (ii) retrieval-augmented generation (RAG) with varying chunk sizes and k-values, (iii) a full-context approach that processes the entire conversation history, (iv) an open-source memory solution, (v) a proprietary model system, and (vi) a dedicated memory management platform. Empirical results show 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 configuration. Beyond accuracy gains, we also markedly reduce computational overhead compared to full-context method. In particular, Mem0 attains a 91% lower p95 latency and saves more than 90% token cost, offering a compelling balance between advanced reasoning capabilities and practical deployment constraints. Our findings highlight critical role of structured, persistent memory mechanisms for long-term conversational coherence, paving the way for more reliable and efficient LLM-driven AI agents.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/1d9c21a0fdb1cc16a32c5d490ebaf98436a23382

Citations in the corpus

• Choosing How to Remember: Adaptive Memory Structures for LLM Agents (2026, unknown): “Mem0 (Chhikara et al., 2025): A flat retrieval-based memory system.”
• MemStrata: 95% and 90.91% Source-Aware Accuracy on LongMemEval-500 and LoCoMo-1540 with a Local Qwen 3.8 27B Q4_K_M Reader (2026, unknown): “Mem0 explores extraction and consolidation of persistent memories, including a graph variant (Chhikara et al., 2025).”
• Do Agents Dream of False Memories? Black-box Visual Attacks on Long-term Memory in Multimodal AI Agents (2026, unknown): “These agents rely on multimodal persistent long-term memory: visual and textual content from past interactions are encoded into a shared embedding space, persisted across sessions, and retrieved at query time [86, 54, 7, 71, 43, 73, 57, 45, 18].”
• Min-Cost Flow Routing for Evidence Assembly in Long Multimodal Documents (2026, unknown): “G 2 -Reader (Du et al., 2026) maintains two evolving graphs consolidated through VLM message passing, an approach related to graph memories for long-horizon agents (Chhikara et al., 2025; Xu et al., 2025b; Rasmussen et al., 2025).”
• ER-MIA: Black-Box Adversarial Memory Injection Attacks on Long-Term Memory-Augmented Large Language Models (2026, unknown): “…to model parameters or the memory system internals. has proposed equipping LLMs with external long-term memory systems that store information from past interactions in memory banks and retrieve relevant memories during inference (Xu et al., 2025; Chhikara et al., 2025; Maharana et al., 2024).”
• Traj-CoA: Patient Trajectory Modeling via Chain-of-Agents for Lung Cancer Risk Prediction (2025, unknown): “These include memory-based methods, which utilize an external memory to store and dynamically update the context [30, 31]; RAG, which”