Reading up on Mem0
6 deep · digging since nov 25, 25
- The Shapes of Agent Memory – Files, Stores, and Experience
Structured stores beat file memory on accuracy and token cost; files win only for small memories or 'I don’t know' answers, and trained experience helps weak models only.
- The State of AI Coding Report 2025
The Greptile report finds AI coding tools increased lines of code per developer by 3.5x and median PR size by 79% in the past year.
- The State of AI Coding 2025
The 2025 AI coding report found developer output up 3.5x and PR size up 79%, with Anthropic SDK closing the gap on OpenAI.
- Universal LLM Memory Does Not Exist
Benchmarking Mem0 and Zep on MemBench reveals they cost 14–77x more and are 31–33% less accurate than naive long-context, debunking the promise of universal LLM memory.