The latest articles on DEV Community by razvanftbl-ai (@razvanftblai). https://dev.to/razvanftblai https://media2.dev.to/dynamic/image/width=90,height=90,fit=cover,gravity=auto,format=auto/https:%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Fuser%2Fprofile_image%2F4192498%2F5e5b8415-da99-4b37-ac09-ba0ef724919e.png https://dev.to/razvanftblai en razvanftbl-ai Sun, 18 Oct 2026 16:53:06 +0000 https://dev.to/razvanftblai/connecting-notion-to-cognee-building-long-term-memory-for-ai-agents-1hg1 https://dev.to/razvanftblai/connecting-notion-to-cognee-building-long-term-memory-for-ai-agents-1hg1 <p>AI agents often lose context across sessions. By integrating Notion with Cognee, agents can automatically ingest workspace documentation and convert it into an interconnected Knowledge Graph.</p> <p>How it works<br> I developed NotionLoader using the official notion-client Python SDK. It fetches pages and databases, extracts text content, and passes it to Cognee's ingestion pipeline.</p> <p>Python<br> from notion_loader import NotionLoader<br> import cognee</p> <p>loader = NotionLoader()<br> pages = loader.load_data()</p> <p>for page in pages:<br> cognee.add(f"Title: {page['title']}\n\n{page['content']}")</p> <p>cognee.cognify()<br> This brings seamless knowledge graph memory to any Cognee agent working with Notion documents!</p> agents ai llm python