Practical AI guides
Retrieval & memory
Explore document retrieval and persistent memory through their storage, context, and maintenance tradeoffs.
Where to start
Retrieval design starts with the documents and questions you need to support. Compare how systems select context, handle updates, and preserve provenance before treating a retrieval technique as a universal improvement.
- How is relevant context selected?
- What happens when documents or memories become stale?
- What storage and model calls does retrieval require?
Practical guides
Why RAG Gives Wrong Answers With Relevant Documents
Why RAG gives wrong answers: Trace evidence through retrieval, context assembly and generation. Target the boundary losing the required facts.
Explore the guideAgent Memory vs Checkpoints: What Should You Persist?
Agent memory vs checkpoints: Separate knowledge, execution progress and scheduling. Use a refund scenario to plan recovery and protect external actions.
Explore the guideExplore the reports
PipesHub for AI Agents: Permission-Aware Retrieval Overview
3.8Kstars
Quivr V2 Explained: Durable Ingestion and Vector Search
39.6Kstars
Vespa Vector Search: In-Engine Ranking vs Separate Retrieval
7.1Kstars
mcp-memory-service Explained: Persistent AI Agent Memory
2Kstars
HelixDB Explained: Graph, Vector and Full-Text Search
5.9KstarsPageIndex for RAG: Document-Tree Retrieval Overview
35.5Kstars