Anupam1612/memeval: Evaluation framework for agent memory systems (opens in new tab)

How We Built memeval: A Testing Framework for AI Agent Memory Every AI agent stack has testing tools. Prompts have LangSmith. RAG pipelines have Ragas. APIs have Postman. But when it comes to memory, the thing that makes your agent remember who the user is, what they said, and what they want, there was nothing. No way to test if your agent will forget a customer's name mid-conversation. No way to catch stale data being returned after a correction. No way to verify that one user's private data...