ai-memory

The tweet highlights the need for clear separation between AI memory in work and personal contexts, reacting to Claude's new unified memory feature across chat and Cowork.

Anthropic updated Claude Cowork to merge its memory system with chat, enabling seamless context retention across interactions and providing user controls for stored information.

A user reports that their Claude AI model lost all its memory and custom settings, seeking advice on how to recover or fix it.

The team is phasing out the Membrane system in favor of the more powerful Meron, whose core breakthrough involves introducing the 'meaning atoms' concept. By storing raw information and multiple representations, it enables flexible and powerful AI memory.

The author proposes that AI memory should evolve beyond remembering facts to understanding a person's journey and history, and introduces 'innernet' as a persistent context layer for personal AI.

An experiment in Seoul showed that deleting 68% of an AI's memory file, specifically adjectives, improved response quality, using OpenAI to grade Claude's memory in a systematic evaluation.

This article highlights that benchmark scores for Engrava, a memory layer tool, can vary due to reader or judge stage variance even when retrieval results are unchanged, using LongMemEval results to illustrate the issue.

Micron Technology is investing $10 billion over a decade in a new Boise research lab to advance AI memory technologies amid rising demand for AI infrastructure.

Microsoft has released an archived reference implementation called Kernel Memory for building RAG pipelines, which ingests data, embeds it, and provides cited answers, but it is intended as a learning resource, not production software.

The Lindy Chrome extension brings AI assistance directly into Gmail, using accumulated memories to draft replies and organize emails, reducing the need to switch to separate interfaces.

The article argues that vector databases alone act as data graveyards without true memory capabilities, and describes building a local AI memory layer with contradiction detection and forgetting cycles on top of Actian VectorAI DB.

Memvid is a tool that compresses the AI memory system into a single file, supporting vector search and full-text retrieval, written in Rust, with high performance and portability.

The article addresses the measurement problem in AI memory and notes MemoraX AI's #1 ranking in the first Agent Memory Leaderboard for commercial products, highlighting advancements in memory systems for agents.

The author compared four hosted memory tools to Claude Code's built-in memory for AI agents, finding Mitosis Cortex provided the largest accuracy boost at 43.1%, with Hyperspell and Mem0 nearly tied, and Supermemory far behind. The post recommends using a hosted memory API over built-in memory for portability and performance.

Wispr Flow's Notetaker integrates with AI agents via MCP to remember and retrieve exact conversations from past meetings, eliminating the need to dig through transcripts.

Introducing Memmy, an open-source AI memory tool that remembers projects, skills, and business process diagrams across tools. Through real-world tests, it demonstrates the ability to locate local projects, invoke Skills, and connect to business agents, emphasizing its core concept of letting multiple AI tools share a single working memory.

Twin is an open-source research project that aims to give AI systems continuous, cumulative understanding by correlating events and building reusable situation models, rather than reconstructing context from scratch each conversation. A demonstration shows Claude Sonnet 4.6 using Twin's MCP server to answer questions about a project without any custom memory or local files.

An essay arguing that compression, not longer context windows, is the load-bearing primitive for long-term AI memory and relational continuity, drawing an analogy to compute and storage in computing.

The author built mem-port, a local MCP server that gives AI copilots (ChatGPT, Claude Code, Cursor, Windsurf) shared long-term memory via embedded SurrealDB, solving context drift between AI tools.

An analysis of the current state of AI memory systems, arguing that the focus has shifted from storing more data to defining how memory should behave—covering governance, observability, lifecycle management, and interoperability.