<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Semantic-Memory on Noureddine RAMDI</title><link>https://ramdi.fr/tags/semantic-memory/</link><description>Recent content in Semantic-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/semantic-memory/index.xml" rel="self" type="application/rss+xml"/><item><title>LycheeMemory: a lightweight semantic long-term memory framework for LLM agents</title><link>https://ramdi.fr/github-stars/lycheememory-a-lightweight-semantic-long-term-memory-framework-for-llm-agents/</link><pubDate>Mon, 04 May 2026 10:23:02 +0000</pubDate><guid>https://ramdi.fr/github-stars/lycheememory-a-lightweight-semantic-long-term-memory-framework-for-llm-agents/</guid><description>LycheeMemory offers a lightweight semantic memory system for LLM agents, cutting token use by 71% and costs by 55% compared to native memory, with SQLite + LanceDB backend and REST/MCP APIs.</description></item><item><title>memU Bot: structured semantic memory for enterprise AI agents</title><link>https://ramdi.fr/github-stars/memu-bot-structured-semantic-memory-for-enterprise-ai-agents/</link><pubDate>Mon, 04 May 2026 10:23:01 +0000</pubDate><guid>https://ramdi.fr/github-stars/memu-bot-structured-semantic-memory-for-enterprise-ai-agents/</guid><description>memU Bot replaces flat memory with a semantic memory layer, cutting token use by 90%. It supports Telegram, Discord, Slack, and Feishu with quick setup and MCP integration.</description></item></channel></rss>