Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

MemMachine: A Ground-Truth-Preserving Memory System for Personalized AI Agents

Shu Wang, Edwin Yu, Oscar Love, Tom Zhang, Tom Wong, Steve Scargall, Charles Fan

Abstract

Large Language Model (LLM) agents require persistent memory to maintain personalization, factual continuity, and long-horizon reasoning, yet standard context-window and retrieval-augmented generation (RAG) pipelines degrade over multi-session interactions. We present MemMachine, an open-source memory system that integrates short-term, long-term episodic, and profile memory within a ground-truth-preserving architecture that stores entire conversational episodes and reduces lossy LLM-based extraction. MemMachine uses contextualized retrieval that expands nucleus matches with surrounding context, improving recall when relevant evidence spans multiple dialogue turns. Across benchmarks, MemMachine achieves strong accuracy-efficiency tradeoffs: on LoCoMo it reaches 0.9169 using gpt4.1-mini; on LongMemEvalS (ICLR 2025), a six-dimension ablation yields 93.0 percent accuracy, with retrieval-stage optimizations -- retrieval depth tuning (+4.2 percent), context formatting (+2.0 percent), search prompt design (+1.8 percent), and query bias correction (+1.4 percent) -- outperforming ingestion-stage gains such as sentence chunking (+0.8 percent). GPT-5-mini exceeds GPT-5 by 2.6 percent when paired with optimized prompts, making it the most cost-efficient setup. Compared to Mem0, MemMachine uses roughly 80 percent fewer input tokens under matched conditions. A companion Retrieval Agent adaptively routes queries among direct retrieval, parallel decomposition, or iterative chain-of-query strategies, achieving 93.2 percent on HotpotQA-hard and 92.6 percent on WikiMultiHop under randomized-noise conditions. These results show that preserving episodic ground truth while layering adaptive retrieval yields robust, efficient long-term memory for personalized LLM agents.

MemMachine: A Ground-Truth-Preserving Memory System for Personalized AI Agents

Abstract

Large Language Model (LLM) agents require persistent memory to maintain personalization, factual continuity, and long-horizon reasoning, yet standard context-window and retrieval-augmented generation (RAG) pipelines degrade over multi-session interactions. We present MemMachine, an open-source memory system that integrates short-term, long-term episodic, and profile memory within a ground-truth-preserving architecture that stores entire conversational episodes and reduces lossy LLM-based extraction. MemMachine uses contextualized retrieval that expands nucleus matches with surrounding context, improving recall when relevant evidence spans multiple dialogue turns. Across benchmarks, MemMachine achieves strong accuracy-efficiency tradeoffs: on LoCoMo it reaches 0.9169 using gpt4.1-mini; on LongMemEvalS (ICLR 2025), a six-dimension ablation yields 93.0 percent accuracy, with retrieval-stage optimizations -- retrieval depth tuning (+4.2 percent), context formatting (+2.0 percent), search prompt design (+1.8 percent), and query bias correction (+1.4 percent) -- outperforming ingestion-stage gains such as sentence chunking (+0.8 percent). GPT-5-mini exceeds GPT-5 by 2.6 percent when paired with optimized prompts, making it the most cost-efficient setup. Compared to Mem0, MemMachine uses roughly 80 percent fewer input tokens under matched conditions. A companion Retrieval Agent adaptively routes queries among direct retrieval, parallel decomposition, or iterative chain-of-query strategies, achieving 93.2 percent on HotpotQA-hard and 92.6 percent on WikiMultiHop under randomized-noise conditions. These results show that preserving episodic ground truth while layering adaptive retrieval yields robust, efficient long-term memory for personalized LLM agents.

Paper Structure

This paper contains 70 sections, 3 figures, 16 tables.

Table of Contents

  1. Introduction
  2. Contributions
  3. Related Work
  4. Memory for AI Agents
  5. Existing Memory Systems
  6. Memory Benchmarks
  7. Memory Types in Cognitive Science
  8. Memory Types for AI Agents
  9. Episodic Memory
  10. Semantic Memory (Profile Memory)
  11. Procedural Memory
  12. Temporal Awareness
  13. Episodic vs. Semantic: When to Use Each
  14. MemMachine Architecture
  15. System Overview
  16. ...and 55 more sections

Figures (3)

  • Figure 1: MemMachine system architecture. Clients (AI agents, Python SDK, MCP servers) access MemMachine through REST API and SDK interfaces. Internally, episodic memory comprises working memory (short-term) and persistent memory (long-term), while semantic memory stores user profiles. All memory types are backed by SQL, vector, and graph databases.
  • Figure 2: Memory recall workflow. The query passes through STM, LTM vector search, contextualization, deduplication, reranking, and chronological sorting before returning results.
  • Figure 3: Retrieval Agent tool tree. The ToolSelectAgent classifies each query and routes it to one of three strategies. All strategies ultimately delegate to the same declarative memory search, ensuring that index and reranker improvements propagate automatically.