GraphRAG vs RAPTOR vs HippoRAG: how to pick a RAG architecture for AI agents
MaryamMiradi · x · 2026-11-08
Maryam Miradi compares three mainstream RAG architectures: RAPTOR (tree-organized chunks with hierarchical retrieval), GraphRAG (entity-relationship knowledge graphs for connected queries), and HippoRAG (associative memory for multi-step retrieval). The choice affects data ingestion, chunking, knowledge representation, retrieval, and context construction. She suggests asking: does your data have hierarchy, do you need entity connections, do questions span multiple documents, and what context does the LLM need?
More from coding & agent
- Agent S4 lets agents evolve reusable computer-use interfaces from their own task experience — burkov · 2026-11-08
- Running 50-100 Agents, Dev Weighs Local Decision Models to Cut Latency — f1yingbanana · 2026-11-08
- This PM replaced the PRD with an interactive Claude artifact — PawelHuryn · 2026-11-08
- Spacedrop lets you drag-and-drop code to deploy in seconds, no GitHub push needed — saheedniyi_02 · 2026-11-08
- Beam's technical report details its sandwich architecture — brandondamos · 2026-11-08
- LangChain's async subagents: orchestrator stays responsive while background workers run long tasks — hwchase17 · 2026-11-08