看看cognee怎么把RAG、GraphRAG和短期记忆揉成一个统一层，还能自动建知识图谱，团队也能共享记忆，加上TurboQuant压缩搞定海量图数据。
cognee的Dave Nielsen在Vector Space Day SF演讲中展示了AI记忆的进化方向：从简单提示存储到自动构建知识图谱。系统从聊天、提示、智能体交互中提取实体和关系，向量存储在Qdrant，图谱关系存储在Neo4j，实现RAG、GraphRAG与短期记忆的统一层。AI记忆正从单个智能体扩展至团队和组织，例如通过学习提示的入职系统或共享知识库。cognee与Qdrant连接器新增TurboQuant支持，对知识图谱的量化效果比常规向量存储更显著，因为图数据规模增长更快。
At Vector Space Day SF, Dave Nielsen from @cognee_ gave an amazing talk on where AI memory is headin...
At Vector Space Day SF, Dave Nielsen from @cognee_ gave an amazing talk on where AI memory is heading: from simple prompt storage to full knowledge graphs built on the fly, combining RAG, GraphRAG, and short-term memory into one unified layer. A few things that stood out: → @cognee_ builds knowledge graphs automatically, extracting entities and relationships from chats, prompts, agent interactions, and pipelines, storing vectors in @qdrant_engine and graph relationships in @neo4j → AI memory is expanding beyond individual agents to teams and organizations, think onboarding systems that learn from prompts, or shared knowledge bases that grow smarter over time → The cognee x Qdrant connector now includes TurboQuant support, and the impact is even bigger for knowledge graphs than regular vector storage, because graph data explodes in size and quantization cuts it down significantly Full talk is live on our youtube channel: youtube.com/watch?v=UKw6PU… 💬 1 🔄 0 ❤️ 2 👀 117 📊 2 ⚡