Berkeley PhD thesis presents a four-part framework for generalist robots: BridgeData V2 dataset (60k trajectories), Octo policy (800k demos, 29% better zero-shot), CrossFormer (single policy across 20 embodiments, 73% success), and MEM (multi-scale memory for 15-min tasks).
OpenWiki, an open-source CLI tool from LangChain, solves AI agents' lack of long-term memory by compiling codebases into structured Markdown wikis with verifiable claims, enabling agents to reuse project understanding across tasks instead of re-scanning code each time.
OpenWiki, an open-source CLI tool from LangChain, generates structured Markdown wikis from codebases to serve as long-term memory for AI coding agents, featuring Claims-based traceability, incremental updates via CI, OKF format support, and multi-model provider compatibility, reducing token consumption compared to RAG approaches.
LangChain's OpenWiki compiles codebases into structured Markdown wikis that serve as persistent, queryable memory for AI coding agents, using Deep Agents for analysis, Claims for traceability, incremental updates, and CI automation to replace repeated code scanning with a compiler-style approach.
Tencent's T-Mem introduces associative recall for LLM agents by pre-storing trigger cues during memory writing, enabling retrieval via semantic associations rather than surface similarity, achieving SOTA on LoCoMo and LoCoMo-Plus benchmarks with minimal performance drop on associative tasks.
This article analyzes how 2026 voice AI systems, with sub-200ms latency, end-to-end architectures, emotion recognition, and long-term memory, foster emotional dependency, illustrating the shift from tool to companion through technical mechanisms and case studies, and suggests boundaries for healthy coexistence.
OpenViking, an open-source context database from Volcano Engine with 32k GitHub stars, solves AI agent memory overflow by storing long-term memory, project resources, and skills in a virtual file system with three-layer summaries, traceable retrieval, and automatic memory consolidation, integrating with major coding agents like Codex and Cursor.
The article explains why AI coding assistants frequently lose context, breaks down the concepts of context windows, compression, and long‑term memory, and shows how the open‑source Magic Context plugin implements a capture‑consolidate‑recall memory loop to keep agents aware of project history across sessions and tools.
The article analyzes the recurring problem that advanced coding agents forget project context across sessions, introduces MemoraX Code’s dual local‑repo and cloud‑based long‑term memory system, and presents benchmark and experimental results that show substantial improvements in task success, cost efficiency, and alignment with developer expectations.
Within a day of release, DeepSeek Harness attracted over 700 GitHub repositories, offering plugins for multi‑agent teams, file referencing, cross‑session memory, Claude integration, UI enhancements, and a collection of 18 nostalgic mini‑games, turning the platform into a highly customizable AI workspace.
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.
The article explains why memory is the decisive factor for AI agents, breaks down short‑term, working, and long‑term memory, quantifies productivity gains, and offers concrete techniques for balancing token costs with task coherence.
The article argues that long-term memory in AI agents introduces governance challenges beyond storage, requiring three boundaries—retention, invocation, and exit—to prevent outdated or temporary information from incorrectly influencing actions, illustrated by a workflow change scenario and aligned with emerging AI regulations.
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.
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.
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.
DM0.5 advances the VLA paradigm by adding zero‑shot capability, efficient fine‑tuning, up to 60‑second memory, stronger resistance to visual and human interference, and cross‑robot transfer, achieved through long‑history modeling, embodied reasoning tasks, trajectory‑alignment supervision, and rigorous multi‑source data cleaning pipelines.
memU is an open‑source Python library and CLI that gives AI coding agents persistent memory by converting past conversations, code, documents, and media into a structured Markdown file tree, allowing agents to retrieve only the needed context instead of re‑entering project details each session.
mem0 is an open‑source AI memory layer that adds long‑term, cross‑session memory to LLM‑based agents, allowing them to retain user preferences, conversation history, and task progress, reducing token usage and latency while integrating with popular models via simple add/search APIs.
This article explains how to integrate Claude Code’s auto‑memory mechanism into Spring AI by using AutoMemoryTools and AutoMemoryToolsAdvisor, compares three integration options, shows the request workflow, memory file formats, and provides concrete code snippets and consolidation strategies for persistent, typed long‑term memory.
When an AI agent runs for months, expired logs and test dialogs fill the token pool, diluting attention and causing contradictory answers; a three‑step freshness scoring and pruning process restores accuracy, cuts token waste by 70% and reduces task latency by 60%.
The article analyzes why Claude Code forgets project context across sessions, explains the limitations of short‑term AI chat windows, and shows how the claude‑mem tool extracts, compresses, and re‑injects essential project experience to provide high‑signal long‑term memory for safer, more context‑aware development and testing.
The article examines the inherent limits of traditional AI context memory, surveys three common memory implementations, introduces TencentDB Agent Memory's hierarchical long‑term and symbolic short‑term architecture, presents benchmark gains (recall up to 167% and token savings over 60%), and provides step‑by‑step deployment and optimization guidance.
This article explains Amazon Bedrock AgentCore Memory’s two‑layer design that separates raw interactions from extracted insights, details built‑in, override and self‑managed strategies, shows Python configuration and three demo scenarios that illustrate cross‑session continuity, semantic deduplication, and episodic reflection, and discusses namespace organization, retrieval settings, and failure handling.
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.
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.
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.
The article explains why large language models lack persistent memory, introduces a three‑layer memory architecture for AI agents—sensory, working, and long‑term memory—and details how vector databases, embedding models, and retrieval strategies enable cross‑session knowledge retention and personalized assistance.
At the 2026 China Database Technology & Industry Conference, DM unveiled GDMBASE V4.0, a graph database that natively fuses vectors and graphs, introduces HyperRAG, long‑term memory, and a natural‑language agent, and delivers sub‑500 ms retrieval, 30% higher recall and 60% lower hallucination rates for AI workloads.
CAMBRIDGE's new ATM‑Bench evaluates AI assistants' ability to retrieve personal memories spanning years across multimodal data, revealing that leading agents like OpenClaw, Codex, and Claude Code achieve under 40% accuracy and struggle despite extensive toolchains, highlighting a fundamental long‑term memory challenge.
This article explains how AI agents store information using short‑term (context window) and long‑term (vector database, RAG, knowledge graph) memory, illustrates the concepts with everyday analogies, and shows how proper memory design improves real‑world applications like customer service bots and personal assistants.
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.
The article examines how the evolution of large‑language‑model memory is shifting from expanding context windows to building controllable, auditable long‑term memory systems, comparing strategies of OpenAI, Anthropic, Google, Microsoft and Meta, and outlining future trends such as automatic memory policies, multimodal storage, agent‑shared memory, and memory‑reasoning integration.
The article introduces the Keyframe‑Chaining VLA (KC‑VLA) framework, which replaces dense video sampling with semantic keyframe linking to provide robots with global temporal awareness, presents a new long‑term memory benchmark, and demonstrates superior performance in both simulation and real‑world robotic experiments.
The paper introduces MemPO, a self‑memory strategy optimization algorithm that lets large language model agents actively manage their memory, dramatically improving accuracy on complex multi‑step tasks while reducing token consumption by up to 73%, and validates the approach with extensive experiments and analysis.
The article explains why large language models lack persistent memory due to the stateless Transformer architecture, breaks down the four dimensions of memory loss, surveys seven technical approaches, three product implementations, and emerging research, and discusses security and privacy implications.
The article explains how to engineer persistent, cross‑session memory for AI agents by persisting key user facts, task states, and decisions in a multi‑layer storage architecture, detailing retrieval before each request and update after each interaction.
The article explains why AI agents need a dedicated memory system, describes a three‑layer memory architecture (working, short‑term, long‑term), and outlines four critical design decisions—what to write, when to read, how to update/forget, and isolation—illustrated with real‑world examples and industry solutions.
This guide explains how Dify manages multi‑turn conversation context through short‑term and long‑term memory, offers compression strategies, integrates knowledge‑base retrieval, provides prompt orchestration templates, and shows API examples for fine‑grained control, with practical configuration tips for various use cases.
This article explains how the combination of Hologres, a unified real‑time data warehouse, and Mem0, an open‑source LLM memory framework, overcomes the limited context window of large language models by providing scalable, low‑latency, and cost‑effective long‑term memory for AI applications.
The article explains the shortcomings of OpenClaw's built‑in memory, introduces MemOS as a cloud‑or‑local long‑term memory service that reduces token consumption by up to 72%, details installation and configuration steps, compares cloud and local plugins, and demonstrates improved recall and multi‑agent collaboration.
The ICLR 2026 paper introduces MemGAS, a multi‑granularity memory framework that organizes dialogue history into session, turn, summary, and keyword levels, dynamically associates them with a Gaussian‑Mixture Model, selects the optimal granularity via entropy‑based routing, and achieves state‑of‑the‑art retrieval and QA performance on long‑term conversational benchmarks.
This article details a 40‑day workflow for creating and evolving eight continuous‑running OpenClaw AI agents using a three‑layer markdown file system—Identity, Operations, and Knowledge—showing how to give agents long‑term memory, self‑healing checks, and coordinated collaboration without databases or message queues.
This article explains how to integrate durable long‑term memory into LangGraph agents, covering memory types, their coordination, limitations of native LangGraph storage, and a step‑by‑step implementation using Trustcall’s schema‑driven extractors for both user profiles and paper collections.
This tutorial walks through adding Retrieval‑Augmented Generation (RAG) and persistent long‑term memory to a LangGraph AI agent, covering concepts, step‑by‑step code for document loading, vector store creation, prompt engineering, memory management, and best‑practice pitfalls.
This article explains how to build a controllable, editable, and cost‑effective long‑term memory system for AI agents by categorizing memory types, structuring a three‑stage pipeline of capture, AI‑driven compression, and smart retrieval, and choosing appropriate storage back‑ends such as files, knowledge bases, or databases.
This article explains how memory systems—both short‑term session memory and cross‑session long‑term memory—address the context‑window limits, token costs, and personalization challenges of AI agents, detailing core concepts, framework differences, integration architectures, context‑engineering strategies, technical components, challenges, and emerging industry trends.
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.
This article explains how AI agents overcome context window limits by using memory systems, distinguishes short‑term (session) and long‑term (cross‑session) memory, compares implementations in Google ADK, LangChain and AgentScope, and outlines context‑engineering techniques, core components, challenges, and emerging trends.
The article explains how context engineering—building a dynamic system that supplies AI with user intent, dialogue history, long‑term memory, external knowledge and tool definitions—outperforms traditional prompt engineering, eliminates hallucinations, and enables AI to complete complex, end‑to‑end tasks.
This guide walks you through creating a Memory v3 module for a Go‑based AI agent, enabling long‑term storage of preferences, tasks, and context so the agent can recall and leverage past interactions for more personalized responses.
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.
Google’s newly unveiled Titans architecture tackles AI’s “forgetfulness” by embedding a Neural Long‑Term Memory (LMM) module that updates model weights during inference using a test‑time training approach and a MIRAS surprise metric, enabling over 2 million‑token context with linear O(N) computation and superior benchmark results versus GPT‑4 RAG.
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.
This guide walks through Coze’s variable and long‑term memory features, showing how to define and use variables for user data, configure persistent memory, and combine both to build personalized, context‑aware AI agents, with step‑by‑step screenshots, code snippets, and real‑world scenarios.
The article explains how Amazon Bedrock AgentCore Memory transforms AI agents from short‑term responders into continuously learning entities by extracting valuable insights, integrating them intelligently, handling edge cases, supporting custom strategies, and delivering high compression rates and low latency for large‑scale deployments.
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.
This tutorial explains how LangGraph handles short‑term memory with InMemorySaver and thread‑isolated checkpoints, how to persist it using PostgresSaver, and how to build long‑term memory with InMemoryStore and PostgresStore, including semantic search and custom storage extensions.
This article explains how Retrieval‑Augmented Generation (RAG) and long‑term memory systems like MenoBase enable large language models to overcome short‑term memory limits, dynamically retrieve up‑to‑date knowledge, and personalize interactions, with practical Dify implementation steps and real‑world use cases across industries.
The article analyzes how Agentic AI coding assistants such as Cursor falter when projects exceed a few thousand lines due to limited context windows, leading to spatial mismatches, temporal forgetting, and redundant implementations, and proposes document‑driven development and long‑term memory as possible remedies.
The paper describes Baidu’s AI‑native advertising platform that employs a multi‑agent architecture built on large‑language models—combining large‑small model collaboration, domain SOP‑driven coordination, and long‑term memory—to enable natural‑language understanding, proactive planning, execution and human‑like responses, illustrated by GBI analytics and JarvisBot operations, delivering higher consumption, accuracy, speed and efficiency.
In this talk, the speaker examines the dual goals of AI agents—being entertaining and useful—while introducing the concepts of fast and slow thinking, multimodal perception, long‑term memory, retrieval‑augmented generation, and tool integration as essential steps toward building truly valuable digital companions.
The article presents Baidu's PLATO open‑domain dialogue system, detailing its evolution from expert‑rule to retrieval‑based and large‑scale generative models, describing its hidden‑variable architecture, major research challenges such as persona stability, long‑term memory, knowledge accuracy, and showcasing real‑world applications and Q&A from a DataFunSummit2022 livestream.
