<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:wfw="http://wellformedweb.org/CommentAPI/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:sy="http://purl.org/rss/1.0/modules/syndication/" xmlns:slash="http://purl.org/rss/1.0/modules/slash/" xmlns:memo="https://memo.d.foundation/ns/feed/1">
  <channel>
    <title>llm - Dwarves Memo</title>
    <atom:link href="https://memo.d.foundation/topics/applied-llm/tags/llm/rss.xml" rel="self" type="application/rss+xml" />
    <link>https://memo.d.foundation/topics/applied-llm/tags/llm</link>
    <description>The newest notes tagged llm on Dwarves Memo.</description>
    <lastBuildDate>Wed, 27 Aug 2025 00:00:00 GMT</lastBuildDate>
    <language>en-US</language>
    <sy:updatePeriod>hourly</sy:updatePeriod>
    <sy:updateFrequency>1</sy:updateFrequency>
    <item>
      <title>Context7 breakdown</title>
      <link>https://memo.d.foundation/breakdown/context7</link>
      <pubDate>Wed, 27 Aug 2025 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[hthai2201]]></dc:creator>
      <description><![CDATA[Technical analysis of Context7, an intelligent documentation indexing and retrieval system that transforms raw library docs into AI-optimized, ranked snippets for real-time LLM context injection]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/breakdown/context7</guid>
    </item>
    <item>
      <title>Dify breakdown</title>
      <link>https://memo.d.foundation/breakdown/dify</link>
      <pubDate>Tue, 19 Aug 2025 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[zlatanpham]]></dc:creator>
      <description><![CDATA[Technical analysis of the Dify platform, its architecture, and engineering decisions that enable scalable LLM application development.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/breakdown/dify</guid>
    </item>
    <item>
      <title>Mem0 &amp; Mem0-Graph breakdown</title>
      <link>https://memo.d.foundation/breakdown/mem0</link>
      <pubDate>Thu, 07 Aug 2025 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[minhluuquang]]></dc:creator>
      <description><![CDATA[Technical analysis of Mem0, a scalable memory architecture for LLMs, and its graph-based variant, Mem0-Graph, designed for long-term conversational coherence.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/breakdown/mem0</guid>
    </item>
    <item>
      <title>Ax framework breakdown</title>
      <link>https://memo.d.foundation/breakdown/ax</link>
      <pubDate>Tue, 29 Jul 2025 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[tuanddd]]></dc:creator>
      <description><![CDATA[Technical analysis of the Ax TypeScript framework for building LLM-powered agents with DSPy capabilities.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/breakdown/ax</guid>
    </item>
    <item>
      <title>Crawl4AI breakdown</title>
      <link>https://memo.d.foundation/breakdown/crawl4ai</link>
      <pubDate>Tue, 29 Jul 2025 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[hthai2201]]></dc:creator>
      <description><![CDATA[Deep dive into Crawl4AI's architecture, data structures, and algorithms - from async pipelines and strategy patterns to browser management and intelligent content extraction for AI workflows.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/breakdown/crawl4ai</guid>
    </item>
    <item>
      <title>Zen MCP breakdown</title>
      <link>https://memo.d.foundation/breakdown/zen-mcp</link>
      <pubDate>Tue, 29 Jul 2025 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[vdhieu]]></dc:creator>
      <description><![CDATA[Technical analysis of the Zen MCP (Model Context Protocol) Server architecture, implementation, and design patterns.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/breakdown/zen-mcp</guid>
    </item>
    <item>
      <title>AI agent explained: LLMs, workflows and agents</title>
      <link>https://memo.d.foundation/topics/agentic/ai-agent-explained</link>
      <pubDate>Mon, 23 Jun 2025 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[tieubao]]></dc:creator>
      <description><![CDATA[Most people confuse LLMs, workflows, and agents, but understanding these three levels unlocks the real potential of AI automation. The key difference lies in who makes the decisions.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/topics/agentic/ai-agent-explained</guid>
    </item>
    <item>
      <title>Append-only concept embedding log</title>
      <link>https://memo.d.foundation/rfc-semantic-reasoning</link>
      <pubDate>Thu, 08 May 2025 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[monotykamary]]></dc:creator>
      <description><![CDATA[RFC proposing a novel approach to track concept evolution using TimescaleDB with pgvector/pgvectorscale, enabling historical semantic analysis and preventing catastrophic forgetting in continual learning systems.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/rfc-semantic-reasoning</guid>
    </item>
    <item>
      <title>Build a brain that never forgets</title>
      <link>https://memo.d.foundation/never-forget</link>
      <pubDate>Thu, 08 May 2025 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[monotykamary]]></dc:creator>
      <description><![CDATA[Explore how we solved the catastrophic forgetting problem in LLMs by building an external knowledge system that mimics learning through context manipulation, without touching the model's parameters.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/never-forget</guid>
    </item>
    <item>
      <title>Data flow in Brainery</title>
      <link>https://memo.d.foundation/brainery-data-flow</link>
      <pubDate>Thu, 08 May 2025 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[monotykamary]]></dc:creator>
      <description><![CDATA[How data flows through Brainery's second brain system, from Discord, Memo Blog, and GitHub sources to TimescaleDB via MCP, with an LLM-powered interface for natural language queries.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/brainery-data-flow</guid>
    </item>
    <item>
      <title>Database design and philosophy</title>
      <link>https://memo.d.foundation/database-design</link>
      <pubDate>Thu, 08 May 2025 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[monotykamary]]></dc:creator>
      <description><![CDATA[A migration-less, append-only database design using TimescaleDB's hypertables and continuous aggregates to capture observational data and detect emerging patterns through LLM analysis.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/database-design</guid>
    </item>
    <item>
      <title>Building use-cases</title>
      <link>https://memo.d.foundation/brainery-use-cases</link>
      <pubDate>Wed, 07 May 2025 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[monotykamary]]></dc:creator>
      <description><![CDATA[Building systems that actually learn and get smarter over time is hard, facing challenges with traditional databases and LLMs. This post outlines an approach to building a true second brain that continuously learns, generates insight, and remembers it through an append-only log and flexible data structures.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/brainery-use-cases</guid>
    </item>
    <item>
      <title>Promoting raw data to insight</title>
      <link>https://memo.d.foundation/promote-data-to-insight</link>
      <pubDate>Wed, 07 May 2025 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[monotykamary]]></dc:creator>
      <description><![CDATA[This post explains the multi-stage process of transforming raw data into structured information, and then synthesizing that information into persistent insight and knowledge within a true second brain, leveraging tools like TimescaleDB and LLMs.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/promote-data-to-insight</guid>
    </item>
    <item>
      <title>Create slides with Overleaf and ChatGPT</title>
      <link>https://memo.d.foundation/create-slides-with-overleaf</link>
      <pubDate>Thu, 20 Mar 2025 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[baenv]]></dc:creator>
      <description><![CDATA[This article shares a workflow for making slide decks with Overleaf and ChatGPT. It solves issues like slow content creation using ChatGPT and formats with Overleaf’s themes. It includes examples, tips, and a Dify automation for engineers.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/create-slides-with-overleaf</guid>
    </item>
    <item>
      <title>Let AI ask you</title>
      <link>https://memo.d.foundation/productivity/let-ai-ask-you</link>
      <pubDate>Mon, 27 Jan 2025 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[tieubao]]></dc:creator>
      <description><![CDATA[Most people give AI commands and expect perfect results, but the most effective approach flips this dynamic. Letting AI ask you questions transforms shallow outputs into precisely targeted solutions.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/productivity/let-ai-ask-you</guid>
    </item>
    <item>
      <title>Mental models for prompting</title>
      <link>https://memo.d.foundation/prompt/mental-models</link>
      <pubDate>Mon, 06 Jan 2025 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[tieubao]]></dc:creator>
      <description><![CDATA[Essential mental models to improve your LLM interactions and prompt engineering effectiveness]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/prompt/mental-models</guid>
    </item>
    <item>
      <title>Quantization for large language models</title>
      <link>https://memo.d.foundation/llm/quantization-in-llm</link>
      <pubDate>Thu, 21 Nov 2024 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[nnhuyhoang]]></dc:creator>
      <description><![CDATA[As large language models (LLMs) continue to evolve, their parameter counts grow exponentially, with some models reaching trillions of parameters. This exponential growth presents significant challenges for deployment on edge devices and in resource-constrained environments due to extensive memory and computational requirements. Quantization emerges as a crucial technique to reduce model footprint while preserving acceptable performance.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/llm/quantization-in-llm</guid>
    </item>
    <item>
      <title>Natural language to database queries: Text-to-MongoDB</title>
      <link>https://memo.d.foundation/llm/text-to-mongodb</link>
      <pubDate>Wed, 13 Nov 2024 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[monotykamary]]></dc:creator>
      <description><![CDATA[An exploration of natural language to database query systems using MongoDB, examining system prompts and implications for data engineering and agentic workflows.]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/llm/text-to-mongodb</guid>
    </item>
    <item>
      <title>GraphRAG - building a knowledge graph for RAG system</title>
      <link>https://memo.d.foundation/llm/graphrag</link>
      <pubDate>Fri, 01 Nov 2024 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[nnhuyhoang]]></dc:creator>
      <description><![CDATA[In baseline Retrieval Augmented Generation (RAG), sometimes the result might not be accurate as expected since the query itself have multiple layers of reasoning or the answer requires traversing disparate pieces of information through their shared attributes in order to provide new synthesized insights. In this post, we will explore a new approach called GraphRAG which combines the strengths of knowledge graphs and large language models to improve the accuracy of RAG systems]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/llm/graphrag</guid>
    </item>
    <item>
      <title>Guardrails in llm</title>
      <link>https://memo.d.foundation/llm/guardrails-in-llm</link>
      <pubDate>Thu, 24 Oct 2024 00:00:00 GMT</pubDate>
      <dc:creator><![CDATA[nnhuyhoang]]></dc:creator>
      <description><![CDATA[Inspite of having strength to process and produce highly coherent human-like, behavior of LLM is unpredictable, so the need of a safety mechanisms and boundaries that control and direct an AI model's behavior to ensure it operates safely, ethically, and within intended parameters is crucial...]]></description>
      <guid isPermaLink="true">https://memo.d.foundation/llm/guardrails-in-llm</guid>
    </item>
  </channel>
</rss>