<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Lancedb on Noureddine RAMDI</title><link>https://ramdi.fr/tags/lancedb/</link><description>Recent content in Lancedb 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/lancedb/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></channel></rss>