# Aashi Dutt

## Area of Expertise

- Agent memory
- Large Language Models (LLM)
- AI infrastructure

## ABOUT THE AUTHOR

#### Recent articles

**[How We Cut Vector Search Latency by 70x](/content/blog/how-we-cut-vector-search-latency-by-70x/index.html)**  
July 17, 2026  
· Engineering

**[Anthropic Claude Pricing Explained: Claude Plans, API Rates & How to Cut Costs](/content/blog/anthropic-claude-pricing/index.html)**  
July 17, 2026  
· Miscellaneous

**[Adding Persistent Memory to Claude with Mem0](/content/blog/adding-persistent-memory-to-claude-with-mem0/index.html)**  
July 16, 2026  
· Engineering

**[Mem0's infer=True vs infer=False: The Fact Your AI Support Bot Forgot](/content/blog/mem0-s-infer-true-vs-infer-false-the-fact-your-ai-support-bot-forgot/index.html)**  
July 15, 2026  
· Engineering

**[Mem0 Claude Connector: Persistent Memory Across Every Chat](/content/blog/mem0-claude-connector-persistent-memory-across-every-chat/index.html)**  
July 14, 2026  
· Engineering

**[5 Agentic Memory Papers at ICML 2026](/content/blog/5-breakthrough-papers-shaping-ai-agent-memory-at-icml-2026/index.html)**  
July 10, 2026  
· Miscellaneous

**[Mem0 vs. Building Your Own Vector Store for Agent Memory](/content/blog/mem0-vs-building-your-own-vector-store-for-agent-memory/index.html)**  
July 9, 2026  
· Miscellaneous

**[Why Your Voice Sales Agent Forgets Every Lead (And the Fix)](/content/blog/why-your-voice-sales-agent-forgets-every-lead-(and-the-fix/index.html)**  
July 8, 2026  
· Engineering