KnowledgeDB.ai
by KnowledgeDB
Active Graph: Event-Sourced Runtime for Agentic Systems
About this podcast
KnowledgeDB.ai is your go-to podcast for diving deep into the infrastructure that powers Generative AI. Each episode explores groundbreaking papers, insightful publications, and emerging technologies shaping the future of AI systems. From distributed computing and graph databases to hardware accelerators and model optimization, we decode the research behind the tech.
Whether you're a developer, researcher, or just curious about the mechanics behind GenAI, KnowledgeDB.ai provides a blend of technical depth and practical insights to keep you informed and inspired. Tune in and stay ahead of the
Episodes
The newest 20 of 39 episodes
- Active Graph: Event-Sourced Runtime for Agentic Systems · 37 minActiveGraph is an event-sourced reactive graph runtime designed to build long-running, auditable AI agents. Unlike traditional frameworks that focus on the model call, this…
- The Graph Engineering Guide 2026 · 44 minThese sources trace the technological shift from basic prompting toward sophisticated graph engineering for managing complex AI agent systems. The first two guides establish a…
- The Context Tax: Rethinking Database Awareness · 18 minRef: https://inferal.com/blog/databases-dont-know-why/ The provided text explores a fundamental limitation in modern database architecture, specifically how these systems…
- Benchmarking and Techniques for LLM Text-to-SQL Systems · 15 minThese sources provide an extensive overview of Large Language Model (LLM)-based Text-to-SQL (NL2SQL) systems, focusing on techniques like prompt engineering, supervised…
- Beyond RAG: Giving AI Agents Persistent Memory with Open Source Tools · 6 minMem0, Graphiti, Cognee, and LangMem are open-source libraries that provide persistent memory for AI agents. Mem0 uses a hybrid database to optimize personalization and reduce…
- Large Language Models for Text-to-SQL: Challenges, Advancements, and Evaluation · 23 minText-to-SQL, translating natural language to SQL, has seen significant advancements due to Large Language Models (LLMs). However, challenges remain in handling complex database…
- LLM Agent Memory Systems: MemGPT, Zep, MEM1 and more... · 19 minThis briefing document synthesizes information from several recent academic papers and a commercial announcement, highlighting cutting-edge developments in enhancing Large…
- MEM1: Synergizing Memory and Reasoning for Agents · 11 minhttps://arxiv.org/abs/2506.15841 The research introduces MEM1, a novel reinforcement learning framework designed to enhance language agents' efficiency and performance in…
- Zep: Temporal Knowledge Graphs for AI Agent Memory · 22 minhttps://arxiv.org/abs/2501.13956 The research introduces Zep, a novel memory service for AI agents, designed to overcome the limitations of current retrieval-augmented…
- The Illusion of Thinking in Large Reasoning Models · 17 minhttps://machinelearning.apple.com/research/illusion-of-thinking The document investigates the capabilities and limitations of Large Reasoning Models (LRMs), a new generation of…
- ROGRAG: A Robust GraphRAG Framework · 23 minRef: https://arxiv.org/html/2503.06474v2 The document introduces ROGRAG, a novel GraphRAG framework designed to improve large language models' (LLMs) performance on specialized…
- The Unprecedented Pace of AI Transformation · 20 minThe provided sources offer a comprehensive overview of the rapid and transformative evolution of Artificial Intelligence. They highlight that AI user adoption, usage, and capital…
- Common Sense is All AI Needs · 18 minhttps://arxiv.org/abs/2501.06642 This manuscript argues that achieving true artificial intelligence (AI) autonomy requires integrating **common sense**, a fundamental ability…
- Universal RAG for Diverse Modalities and Granularities · 13 minhttps://arxiv.org/abs/2504.20734 These sources introduce and describe **UniversalRAG**, a novel framework designed to enhance Retrieval-Augmented Generation (RAG) by…
- What is the Model Context Protocol (MCP)? · 19 minModel Context Protocol (MCP) is presented as a crucial emerging specification for managing how AI models access enterprise data across multiple applications. It addresses the…
- Text2SQL: The Art of Teaching Machines to Speak Database · 12 minRef: https://aiwithmike.substack.com/p/text2sql-the-art-of-teaching-machines Mike Erlihson's Substack post explores the complexities of Text2SQL, the process of enabling…
- Wiz Security GraphDB vs. DeepTempo LogLM: Cloud Defense · 16 minhttps://securityboulevard.com/2025/04/wizs-security-graphdb-vs-deeptempos-loglm/ This Security Boulevard article from April 2025 contrasts Wiz's Security GraphDB, a system that…
- An Algebraic Foundation for Knowledge Graph Construction · 26 minhttps://arxiv.org/abs/2503.10385 The provided document introduces a language-agnostic algebraic foundation for constructing knowledge graphs from diverse data sources. This…
- G-Retriever: Graph Understanding and Question Answering via Retrieval · 13 minhttps://arxiv.org/abs/2402.07630 The paper "G-Retriever" introduces a new method for question answering on textual graphs. It addresses the challenge of enabling users to…
- LLM Post-Training: Reinforcement Learning, Scaling, and Fine-Tuning · 53 minRef: https://arxiv.org/abs/2502.21321 This document provides a comprehensive survey of post-training methodologies for Large Language Models (LLMs), focusing on refining…







