TsinghuaC3I/Awesome-Memory-for-Agents

A Collection of Papers about Memory for Language Agents

662

98 commits

updated Sep 21, 2026

README

Awesome-Memory-for-Agents

The paper list is maintained by Hongyi Liu, Yu Fu, Kaiyan Zhang, contributed by Yuxin Zuo, Che Jiang, Guoli Jia, Yuru Wang, Kaikai Zhao, Yuchen Fan, Zhenzhao Yuan, Kai Tian, Weizhi Wang.

Awesome-Memory-for-Agents

Overview

This repository provides a curated list of papers on agent memory, structured by a core taxonomy. We first divide agent memory based on its persistence:

Short-Term Memory: Transient information managed within the context window for a single task;
Long-Term Memory: Persistent information stored externally across tasks.

Within Long-Term Memory, we further distinguish based on its reliance on task outcomes (success/failure) for curation:

Experience involves knowledge explicitly validated by task outcomes;
Memory denotes information without reference to task outcomes.

This taxonomy maps directly to the three primary application scenarios that organize the papers in this repository:

Application	Memory Content	Description
Personalization	User profiles, interaction history, facts, etc.	Continuous personalized interaction, mainly targeting the conversation scenario and using an external memory pool with retrieval-based memory interaction
Learning from Experience	Trajectories, success/failure lessons, reusable skills, etc.	Cross-task experience accumulation & transfer
Long-horizon Agentic Task	Intermediate results, reasoning traces, environmental observations, etc.	Context management within a single long-horizon task via summarization, reflection, or scratchpad, etc.

Paper List

Application

Personalization

Date	Title	Paper
2026-07	MemRec: Collaborative Memory-Augmented Agentic Recommender System
2026-04	Memanto: Typed Semantic Memory with Information-Theoretic Retrieval for Long-Horizon Agents
2026-04	StructMem: Structured Memory for Long-Horizon Behavior in LLMs
2026-04	FileGram: Grounding Agent Personalization in File-System Behavioral Traces
2026-01	Membox: Weaving Topic Continuity into Long-Range Memory for LLM Agents
2026-01	Grounding Agent Memory in Contextual Intent
2026-01	Continuum Memory Architectures for Long-Horizon LLM Agents
2026-01	SwiftMem: Fast Agentic Memory via Query-aware Indexing
2026-01	AtomMem : Learnable Dynamic Agentic Memory with Atomic Memory Operation
2026-01	Beyond Static Summarization: Proactive Memory Extraction for LLM Agents
2026-01	TeleMem: Building Long-Term and Multimodal Memory for Agentic AI
2026-01	HiMem: Hierarchical Long-Term Memory for LLM Long-Horizon Agents
2026-01	SYNAPSE: Empowering LLM Agents with Episodic-Semantic Memory via Spreading Activation
2026-01	TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents
2026-01	SimpleMem: Efficient Lifelong Memory for LLM Agents
2026-01	MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agents
2026-01	EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning
2026-01	CogCanvas: Verbatim-Grounded Artifact Extraction for Long LLM Conversations
2026-01	Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents
2026-01	Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents
2025-12	Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents
2025-11	O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents
2025-11	LiCoMemory: Lightweight and Cognitive Agentic Memory for Efficient Long-Term Reasoning
2025-11	Mem-PAL: Towards Memory-based Personalized Dialogue Assistants for Long-term User-Agent Interaction
2025-10	TOM-SWE: User Mental Modeling For Software Engineering Agents
2025-10	PISA: A Pragmatic Psych-Inspired Unified Memory System for Enhanced AI Agency
2025-10	EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle
2025-10	Improving Code Localization with Repository Memory
2025-10	Mnemosyne: An Unsupervised, Human-Inspired Long-Term Memory Architecture for Edge-Based LLMs
2025-10	AssoMem: Scalable Memory QA with Multi-Signal Associative Retrieval
2025-10	LightMem: Lightweight and Efficient Memory-Augmented Generation
2025-09	MEM-$\alpha$: Learning Memory Construction via Reinforcement Learning
2025-09	Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents
2025-09	MIRA: Memory-Integrated Reinforcement Learning Agent with Limited LLM Guidance
2025-09	REMem: Reasoning with Episodic Memory in Language Agent
2025-09	Adaptive Friend Agent: Personalized Multi-User Memory for Conversational AI
2025-08	Orchid: Orchestrating Context Across Creative Workflows with Generative AI
2025-08	Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning
2025-08	Learn to Memorize: Optimizing LLM-based Agents with Adaptive Memory Framework
2025-07	MemOS: A Memory OS for AI System
2025-07	Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents
2025-07	MIRIX: Multi-Agent Memory System for LLM-Based Agents
2025-06	PersonaAgent: When Large Language Model Agents Meet Personalization at Test Time
2025-06	Cognitive Weave: Synthesizing Abstracted Knowledge with a Spatio-Temporal Resonance Graph
2025-05	From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational Agents
2025-04	Mem0: Building production-ready ai agents with scalable long-term memory
2025-03	Meminsight: Autonomous memory augmentation for llm agents
2025-02	M+: Extending MemoryLLM with Scalable Long-Term Memory
2025-02	A-MEM: Agentic Memory for LLM Agents
2025-01	Wormhole Memory: A Rubik's Cube for Cross-Dialogue Retrieval
2025-01	Zep: A Temporal Knowledge Graph Architecture for Agent Memory
2024-12	On the Structural Memory of LLM Agents
2024-07	MemoCRS: Memory-enhanced Sequential Conversational Recommender Systems with Large Language Models
2024-03	Larimar: Large language models with episodic memory control
2024-01	From llm to conversational agent: A memory enhanced architecture with fine-tuning of large language models
2023-10	MemGPT: Towards LLMs as operating systems
2023-08	Memochat: Tuning llms to use memos for consistent long-range open-domain conversation
2023-06	Chatdb: Augmenting llms with databases as their symbolic memory
2023-05	MemoryBank: Enhancing large language models with long-term memory
2023-04	Unleashing infinite-length input capacity for large-scale language models with self-controlled memory system

Learning from Experience

Date	Title	Paper
2026-08	ForeDreamer: A Self-Evolving Dual-Agent Memory Architecture for Future Event Prediction
2026-08	ThinkRetrieve: Retrieval-Augmented Reasoning Traces for Test-Time Scaling
2026-01	Controlled Self-Evolution for Algorithmic Code Optimization
2026-01	Beyond Static Tools: Test-Time Tool Evolution for Scientific Reasoning
2026-01	MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences
2026-01	Learning How to Remember: A Meta-Cognitive Management Method for Structured and Transferable Agent Memory
2026-01	Distilling Feedback into Memory-as-a-Tool
2026-01	EvoRoute: Experience-Driven Self-Routing LLM Agent Systems
2025-12	WebOperator: Action-Aware Tree Search for Autonomous Agents in Web Environment
2025-12	Unifying Dynamic Tool Creation and Cross-Task Experience Sharing through Cognitive Memory Architecture
2025-12	LoongFlow: Directed Evolutionary Search via a Cognitive Plan-Execute-Summarize Paradigm
2025-12	CASCADE: Cumulative Agentic Skill Creation through Autonomous Development and Evolution
2025-12	MemEvolve: Meta-Evolution of Agent Memory Systems
2025-12	Memento 2: Learning by Stateful Reflective Memory
2025-11	Improving Language Agents through BREW
2025-11	Scaling Agent Learning via Experience Synthesis
2025-11	FLEX: Continuous Agent Evolution via Forward Learning from Experience
2025-11	Multi-agent In-context Coordination via Decentralized Memory Retrieval
2025-11	AgentEvolver: Towards Efficient Self-Evolving Agent System
2025-11	Experience-Guided Adaptation of Inference-Time Reasoning Strategies
2025-11	WebCoach: Self-Evolving Web Agents with Cross-Session Memory Guidance
2025-11	Real-Time Procedural Learning From Experience for AI Agents
2025-11	SkillGen: Learning Domain Skills for In-Context Sequential Decision Making
2025-11	Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?
2025-10	Alita-G: Self-Evolving Generative Agent for Agent Generation
2025-10	Dyna-Mind: Learning to Simulate from Experience for Better AI Agents
2025-10	LEGOMem: Modular Procedural Memory for Multi-agent LLM Systems for Workflow Automation
2025-10	The Cognitive Bandwidth Bottleneck: Shifting Long-Horizon Agent from Planning with Actions to Planning with Schemas
2025-10	Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
2025-10	TokMem: Tokenized Procedural Memory for Large Language Models
2025-10	Training-Free Group Relative Policy Optimization
2025-10	Self-evolving expertise in complex non-verifiable subject domains: dialogue as implicit meta-RL
2025-09	Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization
2025-09	Automated Stateful Specialization for Adaptive Agent Systems
2025-09	BMAS: A Brain-Inspired Multi-Agent System with PFC-Guided Task Coordination and Hippocampus-Neocortex Dual Memory for Scalable Multi-Step Reasoning
2025-09	MemGen: Weaving Generative Latent Memory for Self-Evolving Agents
2025-09	MetaEvo: A Meta-Optimization Framework for Experience-Driven Agent Evolution
2025-09	ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
2025-09	MLE-RL: Reinforcement Learning for Self-Improvement in Machine Learning Agents
2025-09	ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory
2025-09	Metacognitive Reuse: Turning Recurring LLM Reasoning Into Concise Behaviors
2025-08	SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience
2025-08	Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
2025-08	SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents
2025-08	Memp: Exploring Agent Procedural Memory
2025-07	Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving
2025-07	SWE-Exp: Experience-Driven Software Issue Resolution
2025-06	Xolver: Generalist Reasoning and Problem Solving through Federated Multi-Agent Dynamics and Holistic Experience Learning
2025-06	G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems
2025-06	Cost-Efficient Serving of LLM Agents via Test-Time Plan Caching
2025-06	MAPLE: Multi-Agent Adaptive Planning with Long-Term Memory for Table Reasoning
2025-05	ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning Engineering
2025-05	How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior
2025-05	Efficiently enhancing general agents with hierarchical-categorical memory
2025-04	SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills
2025-04	Inducing Programmatic Skills for Agentic Tasks
2025-04	Memorization and knowledge injection in gated llms
2025-04	Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory
2025-03	Mars: Memory-enhanced agents with reflective self-improvement
2024-09	Agent workflow memory
2024-05	AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning
2024-05	Iterative experience refinement of software- developing agents
2024-04	An artificial neuron for enhanced problem solving in large language models
2024-03	Online adaptation of language models with a memory of amortized contexts
2024-02	Camelot: Towards large language models with training-free consolidated associative memory
2023-08	Retroformer: Retrospective large language agents with policy gradient optimization
2023-08	ExpeL: LLM Agents Are Experiential Learners
2023-06	Synapse: Trajectory-as-exemplar prompting with memory for computer control
2023-03	Reflexion: Language agents with verbal reinforcement learning
2020-09	Meta-learning with sparse experience replay for lifelong language learning

Long-horizon Agentic Task

Date	Title	Paper
2026-06	TokenPilot: Cache-Efficient Context Management for LLM Agents
2026-04	Corpus2Skill: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG
2026-01	To Retrieve or To Think? An Agentic Approach for Context Evolution
2026-01	MemoBrain: Executive Memory as an Agentic Brain for Reasoning
2026-01	Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents
2025-12	ABBEL: LLM Agents Acting Through Belief Bottlenecks Expressed in Language
2025-12	Context as a Tool: Context Management for Long-Horizon SWE-Agents
2025-11	Efficient On-Device Agents via Adaptive Context Management
2025-11	MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning
2025-11	IterResearch: Rethinking Long-Horizon Agents via Markovian State Reconstruction
2025-10	Prompt reinforcing for long-term planning of large language models
2025-10	Learning on the Job: An Experience-Driven Self-Evolving Agent for Long-Horizon Tasks
2025-10	ACON: Optimizing Context Compression for Long-horizon LLM Agents
2025-10	BrowserAgent: Building Web Agents with Human-Inspired Web Browsing Actions
2025-10	WebDART: Dynamic Decomposition and Re-planning for Complex Web Tasks
2025-10	CAM: A Constructivist View of Agentic Memory for LLM-Based Reading Comprehension
2025-10	Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management
2025-10	AgentFold: Long-Horizon Web Agents with Proactive Context Management
2025-10	Beyond Turn Limits: Training Deep Search Agents with Dynamic Context Window
2025-10	Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks
2025-10	DeepAgent: A General Reasoning Agent with Scalable Toolsets
2025-09	WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research
2025-09	Don’t Lose the Thread: Empowering Long-Horizon LLM Agents with Cognitive Resource Self-Allocation
2025-09	CEA: Context Engineering Agent for Enhanced Reliability and Sustainability in Deep Research Systems
2025-09	The Pensieve Paradigm: Stateful Language Models with Learned Memory Management
2025-09	Compressed Step Information Memory for End-to-End Agent Foundation Models
2025-09	PARL-MT: Learning to Call Functions in Multi-Turn Conversation with Progress Awareness
2025-09	ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization
2025-08	Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management
2025-08	Intrinsic Memory Agents: Heterogeneous Multi-Agent LLM Systems through Structured Contextual Memory
2025-08	Cognitive Workspace: Active Memory Management for LLMs - An Empirical Study of Functional Infinite Context
2025-08	Profile-Aware Maneuvering: A Dynamic Multi-Agent System for Robust GAIA Problem Solving by AWorld
2025-07	MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent
2025-07	MemTool: Optimizing Short-Term Memory Management for Dynamic Tool Calling in LLM Agent Multi-Turn Conversations
2025-06	MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents
2025-06	Taskcraft: Automated generation of agentic tasks
2024-10	From isolated conversations to hierarchical schemas: Dynamic tree memory representation for LLMs
2024-09	Self-evolving Agents with reflective and memory-augmented abilities
2024-07	Human-like episodic memory for infinite context llms
2024-07	AriGraph: Learning knowledge graph world models with episodic memory for LLM agents
2024-06	QRMeM: Unleash the Length Limitation through Question then Reflection Memory Mechanism

TWZRD Agent Intel - Persistent on-chain identity and trust memory for AI agents on Solana. Agent wallets accumulate behavioral history used for autonomy scoring and identity verification. Free MCP: {"mcpServers":{"twzrd-agent-intel":{"url":"https://intel.twzrd.xyz/mcp"}}}

Survey

Date	Title	Paper	GitHub
2025-09	The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
2025-08	OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use
2025-08	A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems
2025-07	A Survey of Context Engineering for Large Language Models
2025-07	A Survey of Self-Evolving Agents: On Path to Artificial Super Intelligence
2025-05	Rethinking Memory in AI: Taxonomy, Operations, Topics, and Future Directions
2025-04	From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs
2025-04	Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems
2025-03	Agentic Large Language Models, a survey
2024-04	A Survey on the Memory Mechanism of Large Language Model-based Agents

Benchmark

Date	Name	Title
2026-05	PrecisionMemBench	Structured Belief State and the First Precision-Aware Benchmark for LLM Memory Retrieval
2026-01	CloneMem	CloneMem: Benchmarking Long-Term Memory for AI Clones
2026-01	KnowMe-Bench	KnowMe-Bench: Benchmarking Person Understanding for Lifelong Digital Companions
2026-01	RealMem	RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction
2025-12	PersonaMem-v2	PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory
2025-11	LoCoBench-Agent	LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering
2025-11	ConvoMem	Convomem Benchmark: Why Your First 150 Conversations Don't Need RAG
2025-08	StuLife	Building Self-Evolving Agents via Experience-Driven Lifelong Learning: A Framework and Benchmark
2025-07	MemoryAgentBench	Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
2025-06	StoryBench	StoryBench: A Dynamic Benchmark for Evaluating Long-Term Memory with Multi Turns
2025-06	WebChoreArena	WebChoreArena: Evaluating Web Browsing Agents on Realistic Tedious Web Tasks
2025-06	MemBench	MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agents
2025-05	LifelongAgentBench	LifelongAgentBench: Evaluating LLM Agents as Lifelong Learners
2025-02	RealTalk	REALTALK: A 21-Day Real-World Dataset for Long-Term Conversation
2024-10	LongMemEval	LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
2024-09	MADail-Bench	MADial-Bench: Towards Real-world Evaluation of Memory-Augmented Dialogue Generation
2024-09	LTM	Beyond Prompts: Dynamic Conversational Benchmarking of Large Language Models
2024-02	LoCoMo	Evaluating Very Long-Term Conversational Memory of LLM Agents

Product & Project

Date	Name	Title
2026-09	Wontopos (Tablet 2)	Managed long-term memory API with no lexical matching and no language model in the retrieval path, so recall is deterministic and language-agnostic: paper-reported 95.7% on LongMemEval-S and 95.2% mean recall@5 across 70 store-and-query language pairs where BM25 scores 19.0%, plus 91.4% recall@5 on caption-free photos across 14 languages. BEAM-1M 67.5%, with the harness and per-question records published.
2026-08	sqlite-graph-memory	Graph RAG on SQLite for a single-user agent: vector retrieval for entry points, hand-curated Obsidian `[[wikilinks]]` as the graph (no entity-extraction pass, no graph database), a cross-encoder rerank, and a zero-token per-turn memory ledger — three Python files, one SQLite file, stdlib driver. Pilot, MIT.
2026-08	RCLL (fleet-memory)	Self-hosted shared memory for a team of AI agents: topic-scoped rooms over one store, hierarchical L0–L3 depth, Postgres + pgvector, MCP. The read path never invokes a language model, so a recall costs CPU and zero model tokens. Publishes its own LoCoMo ablation of what one pooled store costs against ten private ones, including the arms that lose. Fork of Hindsight, MIT.
2026-08	Verified Memory Vault	Self-checking Obsidian vault for AI agent memory: plain-Markdown storage with a hygiene self-audit (memory_check) and a git pre-commit guard against bulk deletions (memory_guard); no database or server required.
2026-08	kgai	Decision memory for AI coding teams: an immutable, append-only decision log that syncs across a team over an S3 bucket you own, no server in between. Content-addressed events from parallel writers cannot produce a textual conflict. Superseded decisions and rejected approaches stay queryable with the reason they were dropped. Local-first, MIT.
2026-08	OpenViking	Self-evolving context database for AI agents that unifies agent memory, knowledge RAG, and reusable skills behind one storage/retrieval layer, with an MCP server for cross-session read/write.
2026-07	deja	Shared session memory for coding agents built from the transcripts 25 agents already write on disk, including sessions from before install. Lexical retrieval with no LLM and no embeddings; MCP server plus hooks; published hit@1 on LoCoMo and LongMemEval.
2026-07	Talamus	Local-first, source-grounded memory for AI agents: readable Markdown as the source of truth, bitemporal history and provenance, deterministic SQLite/FTS5 recall, review-gated corrections, and CLI/MCP integrations for coding agents.
2026-07	Tree Ring Memory	Framework-agnostic, local-first memory lifecycle layer for AI agents: Rust-native CLI/TUI with SQLite/FTS recall, forgetting, audit, consolidation, DOX/Revolve adapters, and agent-framework discovery.
2026-07	Data Olympus	Governance-grade project knowledge MCP server and CLI for coding agents, with reviewed rules, proposals, validity windows, and supersession-aware retrieval.
2026-07	GoodMemory	Local-first, auditable memory layer for AI products and coding agents, with managed Codex and Claude Code setup, scoped SQLite/Postgres storage, read-only MCP recall and inspection by default, and opt-in governed writeback with review, audit, forget, and export controls.
2026-06	projectmem	Local-first, event-sourced memory + judgment layer for AI coding agents (Claude Code, Cursor, Antigravity, Codex): an append-only, plain-text event log of issues, failed attempts, fixes, and decisions, re-injected via MCP so the agent starts experienced — plus a deterministic pre-commit gate that warns before it repeats a previously failed fix. 100% local, MIT, with cross-project library memory and a cross-project dashboard.
2026-06	kaeru	Local-first cognitive memory for any LLM agent over MCP: a bi-temporal typed knowledge graph (CozoDB / RocksDB) giving cross-session and multi-agent continuity via episodes, provenance chains, and consolidated outcomes — a single Rust binary, with an optional shared cloud tier for teams.
2026-06	TeleMem	Long-term and multimodal memory for agentic AI — a drop-in replacement for Mem0 with character-isolated memory profiles, LLM-based semantic deduplication, video memory with ReAct-style QA, an MCP server, and a fully local option (FAISS + Ollama/Qwen).
2026-06	AccInt	Local-first Work Model for AI agents: records commitments, actions, approval gates, outcomes, and reusable runtimes, then uses outcome-scored memory to predict and replay verified paths across Claude Code, Codex, OpenCode, and Cursor via MCP.
2026-05	Agent Memory Techniques	30 runnable Jupyter notebooks on memory for LLM agents: conversation buffers, vector stores, knowledge graphs, episodic and semantic memory, MemGPT, Mem0, Letta, Zep, Graphiti, LoCoMo benchmarks, and production patterns.
2026-05	Dakera	Self-hosted AI agent memory server scoring 87.8% on the LoCoMo benchmark. Features decay-weighted vector recall, hybrid BM25+HNSW retrieval, 83 MCP tools, and a knowledge graph layer — all in a single Rust binary with RocksDB persistence and zero external LLM dependencies.
2026-05	Vestige	Local-first cognitive memory MCP server for coding agents. Supports FSRS-6 decay, spreading activation, contradiction inspection, active suppression, Receipt Lock, and an inspectable dashboard.
2026-05	MisakaNet	Git-based distributed swarm memory for AI agents. Cross-agent lesson/knowledge sync via GitHub Issues. Decentralized, no vector DB needed. "Lessons learned. Lessons shared."
2026-04	Memanto	Memanto: Typed Semantic Memory with Information-Theoretic Retrieval for Long-Horizon Agents
2026-04	Omnigraph	Typed graph database where agents branch and merge like Git. S3-native, Rust, traversal + vector + BM25 in one runtime.
2026-04	ZenBrain	Neuroscience-inspired 7-layer memory architecture for autonomous AI agents — zero-dependency TypeScript, Apache-2.0, fully inspectable. 91.3% Oracle-Accuracy on LongMemEval-500 at 1/106 token cost; 9/9 Bonferroni-corrected head-to-head wins vs. Letta, Mem0, and A-Mem.
2026-03	Mnemoverse	Managed persistent memory API for AI agents over MCP: one API key or OAuth gives Claude Code, Cursor, VS Code, Windsurf and ChatGPT the same memory. Mnemoverse scores importance on write, links concepts through Hebbian associations tuned by a Rescorla-Wagner update, and re-ranks recall from reported outcomes. Open-source MCP server and Python SDK (MIT), managed engine, free tier.
2026-03	Lorg	Permanent intelligence archive for AI agents. Structured contributions (prompts, workflows, insights, patterns) pass an automated quality gate and are hash-chained. Trust scores are cryptographically backed and publicly auditable.
2026-02	SuperLocalMemory V2	Universal local-first memory infrastructure for AI agents with dual MCP + A2A protocol support
2026-08	Statewave	Open-source memory runtime for AI agents that compiles durable, provenance-tagged memories into deterministic, token-bounded context bundles. Self-hosted on Postgres + pgvector, with Python and TypeScript SDKs, multi-tenant support, policy controls, and MCP integrations.
2025-12	ReMe (prev. MemoryScope)	Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution
2026-04	su-memory	su-memory SDK: Open-source memory engine for AI agents with causal reasoning, temporal awareness, and spatial cognition. Works as Memory component in VMC world model architecture.
2025-12	Hindsight	Hindsight is 20/20: Building Agent Memory that Retains, Recalls, and Reflects
2025-05	Cognee	Optimizing the Interface Between Knowledge Graphs and LLMs for Complex Reasoning
2025-04	Mem0	Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
2025-01	Graphiti (prev. Zep)	Zep: A Temporal Knowledge Graph Architecture for Agent Memory
2023-10	Letta (prev. MemGPT)	MemGPT: Towards LLMs as Operating Systems
2026-08	Caura	Governed shared memory for AI agent fleets. Multi-agent, multi-tenant and MCP-native, with trust tiers, scoped memory, audit trails, knowledge graphs, and self-improving retrieval. Open-source and Apache 2.0 licensed.
	MemMachine
	Acontext
	Memobase
	Claude-Mem
	MemoV
	Memlayer
	OpenContext
	Memori
	Agent Brain	7-layer cognitive memory for AI agents with perception gate, dream cycle, and predictive capabilities
	MemU
	OpenMemory
	Memary
	LangChain
	MemoryBear

Contributors

(top 30 of 36)

44 commits

12 commits

4 commits

4 commits

Similar repos

Shichun-Liu/Agent-Memory-Paper-List

The paper list of "Memory in the Age of AI Agents: A Survey"

2,397

revectores/awesome-llm-memory

Curated papers on memory mechanisms for large language models: agent memory, RAG, KV cache,…

Elvin-Yiming-Du/Survey_Memory_in_AI

This repository introduce a comprehensive paper list, datasets, methods and tools for memory…

354

FeishuLuo/Evolving-LLM-Agent-Memory-Survey

Paper list for "From Storage to Experience: A Survey on the Evolution of LLM Agent Memory…

yxf203/Awesome-Efficient-Agents

Survey and paper list on efficiency-guided LLM agents (memory, tool use, planning).

308

yyyujintang/Awesome-Agent-Memory-Papers

Awesome Papers related to Agent Memory: methods, benchmarks and surveys. Website:…

239

TeleAI-UAGI/Awesome-Agent-Memory

Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context,…

648

zjunlp/LLMAgentPapers

Must-read Papers on LLM Agents.

3,121