<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Agent-Memory on Noureddine RAMDI</title><link>https://ramdi.fr/tags/agent-memory/</link><description>Recent content in Agent-Memory on Noureddine RAMDI</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sat, 23 May 2026 20:41:27 +0000</lastBuildDate><atom:link href="https://ramdi.fr/tags/agent-memory/index.xml" rel="self" type="application/rss+xml"/><item><title>OpenChronicle: an AX-first local memory layer for LLM agents</title><link>https://ramdi.fr/github-stars/openchronicle-an-ax-first-local-memory-layer-for-llm-agents/</link><pubDate>Sat, 23 May 2026 20:41:14 +0000</pubDate><guid>https://ramdi.fr/github-stars/openchronicle-an-ax-first-local-memory-layer-for-llm-agents/</guid><description>OpenChronicle captures macOS accessibility events to build structured local memory for LLM agents. Its async pipeline produces persistent Markdown memory and an SQLite index.</description></item><item><title>agentic-stack: portable multi-agent memory for AI coding assistants</title><link>https://ramdi.fr/github-stars/agentic-stack-portable-multi-agent-memory-for-ai-coding-assistants/</link><pubDate>Tue, 05 May 2026 13:37:39 +0000</pubDate><guid>https://ramdi.fr/github-stars/agentic-stack-portable-multi-agent-memory-for-ai-coding-assistants/</guid><description>agentic-stack provides a harness-agnostic shared memory layer for AI coding agents, enabling seamless context persistence and migration across tools like Claude Code and Cursor.</description></item><item><title>OpenClaw Auto-Dream: sleep-inspired memory consolidation for persistent AI agents</title><link>https://ramdi.fr/github-stars/openclaw-auto-dream-sleep-inspired-memory-consolidation-for-persistent-ai-agents/</link><pubDate>Mon, 04 May 2026 10:23:02 +0000</pubDate><guid>https://ramdi.fr/github-stars/openclaw-auto-dream-sleep-inspired-memory-consolidation-for-persistent-ai-agents/</guid><description>OpenClaw Auto-Dream implements a 5-layer memory model with importance scoring and forgetting curves to consolidate AI agent memories like human sleep. It enables persistent, evolving knowledge.</description></item><item><title>A-MEM: dynamic semantic memory management for LLM agents inspired by Zettelkasten</title><link>https://ramdi.fr/github-stars/a-mem-dynamic-semantic-memory-management-for-llm-agents-inspired-by-zettelkasten/</link><pubDate>Sun, 03 May 2026 00:54:10 +0000</pubDate><guid>https://ramdi.fr/github-stars/a-mem-dynamic-semantic-memory-management-for-llm-agents-inspired-by-zettelkasten/</guid><description>A-MEM is a Python agentic memory system that dynamically organizes LLM agent memories using semantic embeddings and automatic linking, inspired by Zettelkasten.</description></item></channel></rss>