Tagged articles
Agent Memory
99 articles · Page 1 of 1
Hindsight, an open-source agent memory system, moves beyond vector storage by extracting structured facts, fusing semantic, keyword, graph, and temporal retrieval, and continuously consolidating experiences into evolving observations and mental models so agents can apply verified lessons instead of repeating errors.
AI agentsAgent MemoryConsolidation
0 likes · 20 min read


ArchitectNov 14, 2026 · Artificial Intelligence
This article dissects Anthropic's reference architecture for always-on agents, detailing how inbox event queuing, persistent timers, structured memory, deferred tool calls for permissions, and outbox notifications enable tasks to span multiple execution runs across days without human prompting.
Agent ArchitectureAgent MemoryAnthropic
0 likes · 17 min read

KAIST researchers introduce WikiTrace, a provenance-linked memory system for LLM agents that stores experiences with links to raw execution traces, achieving 90.2 average across eight tasks versus 79.5 without memory, and reducing failure rates on previously solvable tasks from 9.7% to 4.5%.
Agent MemoryKAISTLLM Agents
0 likes · 9 min read

The article explains how ontology — shared domain concepts and constraints — combined with memory and recursive self-improvement loops helps coding agents progressively understand project-specific knowledge, detailing a three-layer knowledge graph implemented in Tencent's R&D loop that improved bug localization success from 58% to 65%.
Agent MemoryBug LocalizationCoding Agent
0 likes · 52 min read

Anthropic discloses Claude's four-layer memory architecture—transcripts, notes, wiki, and injected context—plus an offline Dreaming process that corrects errors, showing through Pokemon and code experiments that effective agent memory requires selective retention of implicit rules over volatile facts, not maximal storage.
AI ArchitectureAI agentsAgent Memory
0 likes · 26 min read

Anthropic discloses Claude's production memory architecture: a four-layer pyramid (transcripts, notes, wiki, injected context) with offline 'Dreaming' that corrects errors against ground-truth transcripts, demonstrating 20K token savings and successful Pokemon Red navigation after fixing cascading memory failures.
Agent MemoryAnthropicClaude
0 likes · 22 min read


ArchitectNov 10, 2026 · Artificial Intelligence
Anthropic's research details Claude's four-layer memory architecture—session records, notes, Wiki, and startup context—plus offline Dreaming correction, showing how agents retain cross-session knowledge with concrete examples, evaluation metrics (61% accuracy combining Wiki+search), and a hands-on verification method for building similar systems.
AI agentsAgent MemoryAnthropic
0 likes · 22 min read

Hindsight addresses the failure of vector-based agent memory to learn from corrections by introducing a four-stage pipeline—Retain for structured fact extraction, Recall with hybrid semantic/keyword/graph/temporal search, Consolidation for evolving Observations and Mental Models, and Reflect for layered reasoning—enabling agents to continuously refine knowledge from experience rather than merely storing history.
Agent MemoryHindsightHybrid Retrieval
0 likes · 20 min read


ArchitectNov 7, 2026 · Artificial Intelligence
Anthropic's research shows how a wrong memory note caused Claude to misinterpret its location in Pokémon Red, and how their 'Dreaming' background process uses raw session logs to detect and correct such errors by preserving evidence trails, applicability conditions, and verification methods.
Agent MemoryAnthropicDreaming
0 likes · 18 min read

This article analyzes the evolution of AI agents from executable tools like OpenClaw to personalized continuous assistants and finally to DeepSeek's Super-agent architecture, examining core components, memory systems, multi-agent coordination, and industry adoption data to reveal the engineering challenges of building trustworthy digital collaborators.
AI agentsAgent ArchitectureAgent Memory
0 likes · 49 min read

The Hindsight open-source project addresses AI agents' tendency to repeat corrected errors by replacing simple vector storage with structured fact extraction, hybrid retrieval, and continuous knowledge consolidation into observations and mental models, enabling agents to evolve actionable knowledge from experience rather than just recalling history.
AI agentsAgent MemoryHindsight
0 likes · 20 min read

Nous Research raised $90M to commercialize its open-source Hermes Agent for enterprises by separating the model from the execution runtime, enabling persistent memory and skills, flexible tool integration, and granular permission controls — letting organizations retain control over their AI agent infrastructure while swapping models as needed.
AI Agent PermissionsAgent ArchitectureAgent Memory
0 likes · 23 min read

The article analyzes Hindsight, an open-source agent memory system that moves beyond vector storage by extracting structured facts, fusing multi-path retrieval, and continuously consolidating observations into evolving mental models, enabling agents to learn from corrections and adapt to changing business rules without repeating past errors.
Agent MemoryHindsightKnowledge Consolidation
0 likes · 19 min read

Zhihu shares its production-grade architecture for a multi-tenant Agent Memory service that combines Mem0's fact extraction and lifecycle management with MongoDB's vector and full-text search, enabling multiple specialized agents to accumulate, isolate, and retrieve long-term operational memories reliably.
Agent MemoryMem0Memory Isolation
0 likes · 22 min read

MemAdapter introduces a post-retrieval calibration framework that prevents memory-induced sycophancy in LLM agents by dynamically adapting memory usage to task context through counterfactual induction, context-aware reflection, and evidence-driven reasoning, improving accuracy across multiple benchmarks and memory systems without modifying upstream memory stores.
Agent MemoryContext-Aware ReflectionCounterfactual Induction
0 likes · 7 min read

The article argues that agent long-term memory must distinguish personal preferences, task facts, and enterprise rules, requiring corrections to capture provenance, approval, scope, permissions, and expiry; it details a structured metadata schema, validation across applicable, inapplicable, and revoked scenarios, and propagation of invalidation to indexes, caches, and in-flight tasks while preserving audit history.
AI agentsAgent MemoryException Handling
0 likes · 9 min read

The article analyzes the 2026 emergence of Personal Agents, dissecting their four-component architecture, comparing ten products including Cue, Fo, Dots, Muse, and Grok Bot, and detailing technical challenges in persistent state, memory, identity, triggers, permissions, and failure handling, concluding with a China-specific outlook on ecosystem-embedded agents and trust-based monetization.
2026 AI ProductsAI agent architectureAgent Identity
0 likes · 53 min read

WorldMemArena, a NeurIPS 2026 benchmark from UCSB, Stanford, ETH Zurich, and others, evaluates multimodal agent memory across write, maintain, retrieve, and use stages in dynamic action-world loops, showing high recall rates (86%) don't guarantee correct answers (50%).
Agent MemoryNeurIPS 2026WorldMemArena
0 likes · 9 min read


Didi TechOct 15, 2026 · Artificial Intelligence
causal-memory replaces flat fact recall with a causal graph of decision→outcome edges, using a hippocampal-inspired engine, Pearl's causal ladder, credit assignment via Q-value backprop, and governance checks to cut repeated mistakes by half in real use.
Agent MemoryCredit AssignmentPearl's causal ladder
0 likes · 34 min read

The article explains how memory poisoning attacks persist across sessions in AI agents, details the memoryfield format for auditable storage, proposes a secure write path with trust levels and source tracking, and provides detection queries for identifying poisoned memories.
AI securityAgent MemoryMINJA attack
0 likes · 14 min read

Palantir's August 2026 update to AIP Analyst introduces Skills (reusable analysis instructions) and Analysis Lookup (historical analyses as templates), adding a method-reuse layer to agent memory beyond knowledge retrieval, tightly integrated with Ontology for governed enterprise AI analysis.
AIP AnalystAgent MemoryAnalysis Lookup
0 likes · 11 min read

Redis 8.0 introduces native vector search with Vector Set data type, HNSW indexing, quantization, and the Iris platform for agent memory and context retrieval, enabling semantic caching that cuts LLM costs by 70% and integrates with LangChain4j and Spring AI.
Agent MemoryLangChain4jRAG
0 likes · 26 min read

Within a week of TypeSafe's Jev release, 13 arXiv papers benchmark the decision model across edge orchestration, agent memory, judging, scam detection, video quality, and visual tasks, showing 15-26% lower latency and 70% cost reduction versus LLMs, but with accuracy gaps on complex reasoning and sensitivity to option naming.
Agent MemoryDecision ModelsJev
0 likes · 15 min read

Palantir's AIP Analyst update introduces Skills and Analysis Lookup, adding a method-memory layer that lets agents reuse analysis workflows and tool chains rather than just retrieving past content, all grounded in the Ontology framework for governed enterprise AI.
AIP AnalystAgent MemoryAnalysis Lookup
0 likes · 11 min read

NVIDIA's Harness-of-Harness (HoH) adds an orchestration layer to AI coding agents, using a three-role loop (Planner, Developer, QA Tester) to enable multi-day autonomous development. Experiments on GameCraft-Bench show HoH achieves higher scores with fewer tokens than naive repetition, and ablation studies confirm re-planning, evidence feedback, and code inheritance are each critical. Major tech firms are now productizing agent harnesses as independent infrastructure layers.
AI agentsAgent MemoryGameCraft-Bench
0 likes · 12 min read

This guide compares six major agent memory systems—Mem0, Graphiti, Letta, Cognee, Supermemory, and Mnemovela—across seven decision points including write timing, conflict resolution, forgetting strategies, and context assembly, helping engineers select the right memory architecture for their AI agents.
AI agentsAgent MemoryCognee
0 likes · 30 min read

Palantir's August 18 AIP Analyst update introduces Skills and Analysis Lookup, adding a method-memory layer that lets agents reuse analytical workflows and tool chains instead of just retrieving past content, all grounded in the Ontology framework.
AI agentsAIP AnalystAgent Memory
0 likes · 11 min read

Codex CLI shifts from lossy context compaction to a token-budget system where the model actively monitors remaining tokens, switches context windows on demand, and retains full history via searchable history and notes tools.
AI coding toolsAgent MemoryCodex CLI
0 likes · 8 min read

Palantir's August 18 update to AIP Analyst introduces Skills and Analysis Lookup, adding a "method memory" layer that lets agents reuse analytical workflows and tool chains rather than just retrieving past content, all grounded in the Ontology framework.
AI agentsAIP AnalystAgent Memory
0 likes · 11 min read

This article analyzes MemoHarness, a framework that evolves AI agents by optimizing six external harness dimensions—context assembly, tool interaction, generation control, task orchestration, memory management, and output processing—instead of model weights, demonstrating gains on terminal, coding, and finance tasks while noting limited experimental scale and selective cross-task transfer.
Agent HarnessAgent MemoryExternal System Evolution
0 likes · 22 min read

Hologres evolves from a real-time data warehouse into an AI data infrastructure, integrating multimodal data via Object Tables and Dynamic Tables, providing AI Functions for hybrid search within SQL, an AI Assistant for automated warehouse operations, and a long-term memory service for cross-session agent recall.
AI FunctionsAgent MemoryAlibaba Cloud
0 likes · 15 min read

The article explains that typical agent systems store long‑term memory as raw chat logs embedded in a vector database, which only captures similarity, and introduces MNEMOVELA’s cognition runtime model that classifies memories into types, uses Git‑like branching, hybrid retrieval, and context assembly to provide semantically rich, versioned agent memory.
Agent MemoryHybrid RetrievalMnemovela
0 likes · 6 min read

This guide covers 18 essential Agent Memory interview questions, from why LLMs need memory and the risks of statelessness to practical implementations such as short‑term strategies, long‑term storage options, compression techniques, security concerns, self‑evolving memories, and designing a scalable system for millions of users.
Agent MemoryLLMmemory management
0 likes · 27 min read

Palantir’s August 18 update to AIP Analyst introduces Skills and Analysis Lookup, letting agents store reusable analysis commands and treat past analyses as templates that re‑execute tools on current data, thereby extending Agent Memory from content recall to method reuse within the Ontology‑driven enterprise AI platform.
AIP AnalystAgent MemoryAnalysis Lookup
0 likes · 9 min read

Redis has evolved from a pure cache middleware into a full‑stack AI data infrastructure, offering vector search, native vector sets, semantic caching, and an AI Agent context engine, with sub‑millisecond latency, high throughput, and detailed performance benchmarks that illustrate its strengths and trade‑offs.
AIAgent MemoryJava
0 likes · 15 min read

The article explains why a coding agent may appear to forget earlier decisions, introduces a three‑layer memory system (interaction history, request projection, logical execution chain), and details token‑budget constraints, prompt‑caching trade‑offs, and a suite of context‑compression strategies to keep agents reliable across long conversations.
Agent MemoryLLMPrompt Caching
0 likes · 16 min read

The article reviews recent top‑conference papers on agent memory, explains why current AI assistants lose context across sessions, categorizes memory types, analyzes challenges such as relevance selection, retrieval gaps, staleness, and privacy, and evaluates five leading solutions from A‑MEM to SP‑Mem.
A-MEMAgent MemoryCABLE
0 likes · 11 min read

The article critiques traditional agent‑memory benchmarks for their self‑selected models, judges, and datasets, then explains how the Agent Memory Leaderboard (AML) enforces strict variable control through isolated APIs, version‑hashed contracts, high‑concurrency scheduling, and a 5k‑question blind set, and analyzes the resulting commercial and open‑source rankings, highlighting architectural trade‑offs such as recall, time reasoning, memory governance and safety.
AIAMLAgent Memory
0 likes · 11 min read

The article explains how AMS’s long‑term memory transforms discarded conversation data into reusable knowledge assets by defining various memory strategies, managing ownership, lifecycle, retrieval, and providing practical configuration and best‑practice guidance for AI assistants.
AI assistantAMSAgent Memory
0 likes · 24 min read

The first Agent Memory Leaderboard (AML) debuted on August 12, 2026, crowning MemoraX with a 58.0 score and InvMem as the open‑source champion, while its three‑fold isolation design, multi‑source dataset integration, and rigorous governance set a new, quantifiable standard for long‑term memory in agents, sparking intense community discussion and highlighting emerging trends toward active memory governance, engineering‑level isolation, and full‑chain evaluation.
AMLAgent MemoryLLM
0 likes · 12 min read

The article surveys five emerging approaches to LLM continual learning—external agent memory, context engineering, post‑training, pre‑training, and self‑modifying models—explaining how each tackles the core obstacle of catastrophic forgetting, citing benchmarks such as TRACE, ACE, and SDFT, and reflecting on Karpathy’s ten‑year timeline.
Agent MemoryCatastrophic ForgettingContinual Learning
0 likes · 17 min read

At AICon 2026, Ma Jin explained how Lance’s layered lakehouse format—spanning file, table, index and catalog layers—addresses AI workloads by supporting wide columns, cheap schema evolution, mixed storage and low‑latency random reads, enabling unified handling of training data, RAG retrieval and Agent memory.
AI-native FormatAgent MemoryLance
0 likes · 16 min read

The Agent Memory Leaderboard (AML) debuted on July 29, 2026, offering a unified, reproducible evaluation framework that combines multi‑source text and code memory datasets, standardized protocols, ability profiling, and low‑barrier integration to fairly compare memory systems while providing detailed performance diagnostics and incentives for participants.
AIAgent MemoryLong-term Memory
0 likes · 12 min read


ArchitectAug 6, 2026 · Artificial Intelligence
The article analyzes TencentDB Agent Memory’s design, breaking down its three‑stage write‑read‑governance pipeline, four‑level L0‑L3 hierarchy, object types, recall strategies, conflict handling, sharing rules, long‑task traceability, and practical testing guidelines to ensure past information helps future decisions while preserving provenance and error correction.
Agent MemoryLLMLong-term Memory
0 likes · 22 min read

The Agent Memory Leaderboard (AML), launched on July 29, 2026 by over twenty universities and research institutes, offers a comprehensive, open benchmark that unifies text and code memory evaluation through standardized data, protocols, ability profiling, low‑barrier APIs, and a global competition with rewards.
Agent MemoryEvaluation ProtocolLong-term Memory
0 likes · 13 min read

OpenAI shows that enabling retained reasoning and context compaction boosts ARC‑AGI‑3 performance from 13.3% to 38.3% (about three‑fold) by preserving the agent’s working memory, a finding that reshapes how we evaluate and design AI agents beyond raw model weights.
AI Agent DesignARC-AGI-3Agent Memory
0 likes · 16 min read

Adding memory to agents is now straightforward, but when agents run for weeks across many interactions, the real challenge shifts from merely retrieving past data to determining which past information remains valid, how to manage its lifecycle, and how to govern cost, updates, and deletion, as highlighted by Oracle's technical report and benchmark evaluations.
Agent MemoryLong-Horizon AIMemory Lifecycle
0 likes · 14 min read

The article introduces MemSyco-Bench, a systematic benchmark that reveals how long‑term memory in LLM agents can amplify sycophancy, cause accuracy drops, and expose the need for careful memory utilization rather than mere retrieval.
Agent MemoryLLMMemory Utilization
0 likes · 9 min read

Mandol tackles the fragmented memory problem of LLM agents by unifying representation, storage, and retrieval in a memory‑native architecture; benchmarked on LoCoMo and LongMemEval it achieves up to 92.21% accuracy, 5× faster latency, and runs efficiently on consumer‑grade hardware without external databases.
Agent MemoryLLMhierarchical memory
0 likes · 14 min read

The article analyzes why agents often forget or hallucinate past information, defines three orthogonal memory dimensions, critiques common naive solutions, and presents a four‑module architecture—including extraction, representation, retrieval, and maintenance—plus cross‑cutting concerns, a reference design, failure patterns, and a workload‑driven selection matrix.
Agent MemoryLLMPrompt Caching
0 likes · 24 min read

The article builds an information‑theoretic framework for AI coding, showing how entropy, conditional entropy and mutual information explain why detailed prompts still fail, why new projects succeed more easily than legacy code, and how memory, retrieval and harness engineering can be evaluated to reduce the model's guesswork.
AI codingAgent MemoryHarness Engineering
0 likes · 23 min read

The open‑source Hebb Mind project replicates the brain’s encode‑consolidate‑activate‑forget loop in engineering, replacing simple storage‑retrieval approaches with a four‑stage memory cycle, and demonstrates state‑of‑the‑art performance on LongMemEval and LoCoMo benchmarks while running locally without external services.
AI MemoryAgent MemoryHebb Mind
0 likes · 13 min read

The article explains why AI agents need three distinct memory layers—RAG for external knowledge, Agent Memory for personal and workflow context, and a Knowledge Graph for relational reasoning—detailing their strengths, weaknesses, use‑cases, and a step‑by‑step architecture roadmap.
AI agentAgent MemoryLLM
0 likes · 20 min read

BudgetMem introduces a query‑aware budget‑tier routing mechanism for LLM agents, allowing the memory system to dynamically allocate computational resources based on query complexity and achieving a superior performance‑cost trade‑off on several benchmarks.
Agent MemoryBudget RoutingLLM
0 likes · 9 min read

This article surveys 17 recent core papers that explore how the system‑level harness surrounding large‑model agents can be automatically generated, evolved, and audited, covering topics such as system boundaries, failure‑driven improvement, memory and skill optimization, source‑level rewriting, scaling laws, aging, and safety.
Agent MemoryHarness EngineeringLLM Agents
0 likes · 18 min read

The article analyzes the context fragmentation challenges faced by production‑grade agents—memory loss, workspace inconsistency, and governance gaps—and explains how ContextBucket’s managed service unifies memory and workspace with hybrid retrieval, serverless storage, and multi‑tenant isolation, delivering significant accuracy and cost improvements.
Agent MemoryHybrid RetrievalLLM performance
0 likes · 15 min read

The article presents a comprehensive architecture for production‑grade autonomous agents, detailing failure modes, four distinct memory types, a nightly observation engine that turns patterns into procedural rules, tier‑aware decay scoring, context budgeting, GDPR‑compliant deletion, and a step‑by‑step maintenance pipeline.
Agent MemoryGDPR complianceRAG
0 likes · 31 min read


ITPUBJun 2, 2026 · Databases
Tencent Cloud Database unveils a full‑stack upgrade for the Agent era, introducing Agent Memory, TDSQL Boundless, TDSQL‑C dual‑engine, and DatabaseClaw, each delivering multi‑modal fusion, serverless elasticity, zero‑ETL cloning, and AI‑native query capabilities that reshape how agents store and retrieve data.
AI-native databaseAgent MemoryDatabaseClaw
0 likes · 18 min read

The article analyzes why AI agents forget, then compares three memory architectures—RAG, LLM Wiki, and GBrain—detailing their strengths, weaknesses, scalability, latency, compounding knowledge, and autonomy, and offers guidance on choosing the right approach for different use cases.
AI ArchitectureAgent MemoryGBrain
0 likes · 20 min read


FunTesterMay 19, 2026 · Artificial Intelligence
The article explains why default agent memory is fleeting, proposes a two‑layer design of session and long‑term memory with a post‑session “dreaming” integration step, and shows how selective persistence and shared long‑term storage keep agents continuously improving.
AI ArchitectureAgent MemoryDream Integration
0 likes · 8 min read

MemPrivacy introduces a reversible, fine‑grained privacy layer for edge‑cloud agents, outperforming OpenAI's privacy‑filter by over 50 % F1 while keeping system utility loss under 2 %, thus enabling agents to remain useful without exposing raw sensitive data.
AIAgent MemoryF1
0 likes · 16 min read


ArchitectMay 12, 2026 · Artificial Intelligence
The article dissects Agent Memory, explaining how past observations are written, managed, and read to affect future tasks, highlighting challenges such as relevance, decay, conflict, security, and offering practical design guidelines and architectural options for production‑grade AI agents.
AI ArchitectureAgent MemoryLLM Agents
0 likes · 31 min read

The article explains why large language model agents need dedicated memory systems to overcome limited context windows, outlines short‑term and long‑term memory architectures, storage forms, functional categories, lifecycle operations, control‑policy research, compares leading products, and presents best‑practice engineering guidelines for building scalable, privacy‑aware agent memory pipelines.
Agent MemoryControl PolicyLong-term Memory
0 likes · 25 min read

The article analyzes the limitation of finite LLM context windows for unbounded agent tasks, reviews existing truncation, summarization, and RAG approaches, and presents the Lossless Context Management (LCM) architecture with immutable storage, hierarchical DAG compression, three‑level summarization, and zero‑overhead processing for both short and large‑scale workloads.
AI agentsAgent MemoryAgentic-Map
0 likes · 9 min read

The article analyses why a real agent must have memory, defining memory as an external state that feeds decision‑making, proposing a three‑part architecture (Raw Ledger, Views, Policy), contrasting parametric and non‑parametric approaches, and detailing bottlenecks, temporal handling, and procedural extensions.
Agent MemoryMemory ArchitectureSystem 1 / System 2
0 likes · 46 min read

The article examines why naïvely feeding all dialogue history to large language models is costly and unreliable, and it walks through rolling context windows, inverted‑index pruning, semantic vector search, and GraphRAG as complementary techniques for creating efficient, reasoning‑capable AI agent memory.
AIAgent MemoryGraphRAG
0 likes · 11 min read


ArchitectApr 30, 2026 · Artificial Intelligence
The article dissects Hermes Agent’s four‑layer memory architecture—hot memory, session search, skills, and optional Honcho—explaining how each layer’s cost and purpose differ from OpenClaw’s approach, and why careful placement of facts, history, procedures, and user models leads to more stable, cache‑aware agents.
Agent MemoryContext ManagementHermes Agent
0 likes · 25 min read

The article surveys recent LLM‑based agent memory research, presenting a unified framework that breaks memory systems into four components, detailing their design choices, experimental evaluation on LOCOMO and LONGMEMEVAL, key findings, and a new low‑token SOTA architecture.
Agent MemoryLLMLong‑term Tasks
0 likes · 8 min read

The article explains LangGraph’s checkpoint system that lets agents retain dialogue context, detailing the InMemorySaver for development and PostgresSaver for production, how to use checkpointer.put/get, thread_id for session isolation, manual state manipulation, and time‑travel replay, with full Python examples.
Agent MemoryInMemorySaverLangGraph
0 likes · 5 min read

This article dissects Claude Code's memory system, explains why unstructured memory degrades performance, introduces four distinct memory types with concrete examples and schema, shows how to handle expiration and retrieval strategies, and provides step‑by‑step implementation code to improve agent reliability.
Agent MemoryClassificationLLM
0 likes · 19 min read

The article analyzes Agent memory design by comparing human short‑term and long‑term memory, explains context‑window management strategies, outlines persistent storage options such as vector databases, relational stores, knowledge graphs and fine‑tuning, and presents a three‑layer architecture with write, retrieval and forgetting mechanisms.
Agent MemoryLLMLangChain
0 likes · 15 min read

A comprehensive analysis of over 900 GitHub repositories reveals two distinct paradigms for agent memory—backend storage and context substrates—highlighting their technical differences, strengths, limitations, and the emerging shift toward context engineering for long‑running AI agents.
AIAgent MemoryLLM
0 likes · 15 min read

The article explains how to split an AI agent's memory into short‑term and long‑term layers, compares fixed‑window truncation with rolling summarisation for session memory, and details building a vector‑based long‑term store, its benefits, drawbacks, and governance practices.
Agent MemoryLLMLong-term Memory
0 likes · 6 min read

The article breaks down how to build a three‑layer memory architecture for AI agents—short‑term context windows with sliding‑window summarization, long‑term semantic retrieval via vector databases with selective storage and time decay, and a knowledge‑graph layer for relational reasoning—plus implementation tips and common pitfalls.
Agent MemoryLangChainShort-term Memory
0 likes · 19 min read

This article provides a comprehensive guide to designing, implementing, and evaluating an Agent Memory module for large‑language‑model assistants, covering memory types, short‑ and long‑term storage, conflict resolution, hybrid retrieval, compliance, and practical interview answers.
Agent MemoryComplianceHybrid Retrieval
0 likes · 32 min read

The article analyzes Hermes Agent's self‑improving features, memory architecture, safety defaults, and long‑term personal assistant focus, comparing them with OpenClaw's gateway‑oriented design to help readers decide which framework better fits their automation and personal‑agent needs.
AI agentsAgent MemoryHermes Agent
0 likes · 12 min read

The article introduces instinct, a confidence‑driven memory framework that lets AI coding agents automatically observe, consolidate, and suggest reusable patterns across sessions, using SQLite for storage, MCP for integration, and a Python API for extensibility.
AIAgent MemoryMCP
0 likes · 11 min read

The article examines the noise‑accumulation problem of AI‑Agent memory, explains Claude Code’s Auto Memory and its four‑step Auto Dream consolidation process, details OpenClaw’s three‑stage Dreaming mechanism, compares the two systems across several dimensions, and relates the design to human memory science and practical agent engineering.
AIAgent MemoryAuto-dream
0 likes · 15 min read

This article defines agent memory, outlines its three core components and memory classifications, then provides a detailed comparative analysis of the memory designs in Claude Agent SDK, OpenAI Codex CLI, OpenClaw, and Claude Code, highlighting trade‑offs, implementation details, and engineering implications.
Agent MemoryClaudeContext Management
0 likes · 29 min read

This article dissects Claude Code's memory architecture, explaining its four distinct memory layers, file‑based long‑term storage, dynamic retrieval without embeddings, multi‑stage write paths, and session‑compression strategies, while highlighting design trade‑offs and practical takeaways for building robust AI agents.
AI ArchitectureAgent MemoryClaude Code
0 likes · 20 min read

This tutorial walks through designing and implementing a dual‑stack memory architecture for AI agents—combining episodic vector‑based situational memory with graph‑based semantic memory—using LangChain, FAISS, and Neo4j, and demonstrates a complete end‑to‑end workflow with code examples.
Agent MemoryFaissLangChain
0 likes · 14 min read

This article explains why AI agents need a structured memory module, outlines three memory types from cognitive science, details short‑term and long‑term storage architectures using vector databases, and provides concrete code and management strategies—including conflict resolution, TTL expiration, and privacy compliance—to build a robust Agent Memory system.
Agent MemoryLLMMem0
0 likes · 23 min read

This article breaks down agentic memory into four distinct types—In‑context, External, Episodic, and Semantic/Parametric—explains three forgetting strategies (time decay, importance scoring, periodic consolidation), shows how memory flows through an agent loop, and provides complete Python code using OpenAI embeddings and ChromaDB for a production‑ready memory layer.
Agent MemoryChromaDBLLM
0 likes · 22 min read

The article analyzes why large language models are inherently stateless, outlines a four‑layer memory architecture for AI agents—including working, situational, semantic, and procedural memory—and explains write, retrieval, and forgetting mechanisms along with current tooling such as Mem0 and Letta.
Agent MemoryLLMLetta
0 likes · 9 min read

OpenViking, an open‑source “Agent context database” from ByteDance’s Volcano Engine, replaces flat RAG retrieval with a hierarchical file‑system model, offering layered summaries, recursive directory search, and traceable sessions, but its core still relies on vector retrieval and some features remain placeholders, making it more suited to enterprise agents than hobby projects.
Agent MemoryContext ManagementHierarchical Retrieval
0 likes · 11 min read

The article explains how the ALMA system lets a meta‑agent automatically generate and evolve Python memory modules for agents, replacing brittle handcrafted heuristics with a four‑stage meta‑learning loop, and shows that the resulting designs outperform existing baselines while using far fewer tokens.
ALMAAgent MemoryMeta-learning
0 likes · 9 min read

This article explores a new agent‑optimization paradigm—Memory‑Based Self‑Evolution—detailing how dynamic memory systems such as Dynamic Cheatsheet, ReasoningBank, ACE, and MemGen transform LLM agents from static, parameter‑only models into continuously learning entities that can adapt to real‑world data, with a focus on insurance industry applications.
Agent MemoryLLMinsurance AI
0 likes · 13 min read

The paper introduces xMemory, a hierarchical "split‑aggregate‑retrieve" framework that reduces token usage by up to 30% and improves QA performance by more than 10 points in long‑range agent conversations, outperforming traditional RAG across multiple LLMs.
Agent MemoryHierarchical RetrievalLLM
0 likes · 8 min read


大转转FEFeb 2, 2026 · Artificial Intelligence
This edition of the ZuanZuan Frontend Weekly curates five in‑depth articles covering Moltbot’s underlying gateway architecture, the explosive growth of Moltbook AI agents, practical integration of Alibaba Cloud RDS AI assistants, the design of short‑ and long‑term AI Agent memory systems, and a two‑stage ToolRL approach that dramatically improves AI‑driven recommendation performance.
AI ArchitectureAI OpsAgent Memory
0 likes · 7 min read

This article distills OpenAI's Build Hour on agent memory patterns, explaining why memory is treated as context engineering, detailing short‑term and long‑term memory architectures, outlining practical challenges like token limits, context explosion, and safety guardrails, and offering engineering best‑practices for production‑grade AI agents.
AIAgent MemoryLong-term Memory
0 likes · 20 min read

This article explains how to give large language model agents lasting memory by combining short‑term and long‑term storage in LangGraph, covering concepts, implementation details, database persistence, tool integration, semantic search, memory‑management strategies, checkpoint handling, and a multi‑agent supervisor example.
Agent MemoryLLMLangGraph
0 likes · 43 min read

This article examines the limitations of LLM short‑term context windows and compares three open‑source long‑term memory frameworks—Mem0, Graphiti, and Cognee—by detailing their architectures, storage modes, integration steps, code examples, strengths, drawbacks, and practical selection guidance for building smarter AI agents.
Agent MemoryCogneeGraphiti
0 likes · 20 min read

This article explains the definitions, technical implementations, functions, limitations, and collaborative workflow of short‑term and long‑term memory in large‑language‑model agents, detailing context windows, attention mechanisms, vector storage, retrieval strategies, and future research directions for building personalized, continuously learning AI agents.
Agent MemoryLLMLong-term Memory
0 likes · 11 min read

This tutorial walks you through why LangGraph outperforms LangChain by showing how to build a basic chatbot, integrate tool calls, and add both short‑term and long‑term memory, complete with code examples and visualizations for creating flexible, state‑driven AI agents.
Agent MemoryLLMLangGraph
0 likes · 14 min read

This article provides a comprehensive technical analysis of LLM context, covering its definition, types, tokenization, window‑size evolution, diminishing returns, management techniques such as RAG, CoT, memory‑as‑a‑service, and future challenges like multimodal fusion, privacy, and autonomous agent memory.
Agent MemoryContext ManagementLLM
0 likes · 48 min read

Augment, a newly funded AI programming assistant that tops the SWE‑bench benchmark with a 65.4% score and a 200 k‑token context window, promises massive productivity gains for developers but also introduces sophisticated security threats such as malicious memory prompts, back‑door context injection, compromised guidelines, and risky multi‑task collaboration protocols, prompting calls for layered defenses and vigilant monitoring.
AI programmingAI safetyAgent Memory
0 likes · 11 min read


ArchitectMar 26, 2025 · Artificial Intelligence
This article explains the fundamentals of AI agent memory—including short‑term, long‑term, and working memory types and their storage designs—and then details Dify's knowledge‑base segmentation modes, indexing strategies, and retrieval configurations for effective RAG applications.
Agent MemoryDifyLLM
0 likes · 14 min read


JavaEdgeJun 26, 2024 · Artificial Intelligence
This guide walks through adding ConversationBufferMemory to a LangChain agent, covering tool creation, memory setup, agent initialization with OpenAI function calling, prompt inspection, configuration tweaks using agent_kwargs, and best‑practice considerations for maintaining context in multi‑turn AI conversations.
Agent MemoryConversationBufferMemoryLangChain
0 likes · 8 min read

This article introduces MetaGPT, an open‑source multi‑agent framework that leverages large language models to automate software development, data science, and simulation tasks, detailing its development, impact, experimental results, memory and reasoning enhancements, and comparisons with related systems.
AI researchAgent MemoryLLM Agents
0 likes · 21 min read
