This Startup Is Trying To Solve The AI Memory Problem

ℹ️ EPISODE INFO

Released

January 23, 2026

Duration

17m

Channel

YC Root Access

Watch on YouTube

▶ Open ↗

📝 EPISODE DESCRIPTION

While LLMs continue to evolve, they still struggle with memory. The startup Mem0 is working to change that by building the memory layer for AI agents. In this episode of Founder Firesides, YC’s Nicolas Dessaigne sat down with co-founders Taranjeet Singh and Deshraj Yadav to discuss why agents need persistent memory to improve over time, how Mem0 reduces cost and latency compared to native context stuffing, and why memory must remain neutral across models as AI becomes more agent-driven. Chapters: 00:05 What Is Mem0? 00:49 Traction & Open Source Adoption 01:24 Why Memory Improves AI Agents 02:01 Saving Cost and Latency 02:31 Founder Origins & YC Pivot 05:13 How Mem0 Works Under the Hood 06:04 Hybrid Memory Architecture 07:10 Custom Memory Rules & Expectations 08:00 Real-World Use Cases 10:05 Competing With Model-Native Memory 11:48 Fundraising & What’s Next

🎤 SPEAKERS

• Nicolas Dessaigne

  host

  YC Root Access host and YC partner/interviewer.

• Deshraj Yadav

  guest

  Co-founder/CTO of Mem0; previously led the AI platform team at Tesla Autopilot.

• Taranjeet Singh

  guest

  Co-founder of Mem0 focused on product/traction and company building (non-CTO founder).

🧾 EPISODE SUMMARY

In this episode of YC Root Access, featuring Nicolas Dessaigne and Deshraj Yadav, This Startup Is Trying To Solve The AI Memory Problem explores Mem0 builds neutral, portable memory layer for AI agents and apps Mem0 addresses the core limitation that LLMs are stateless by adding a dedicated memory layer for AI agents and applications.

🔗 RELATED EPISODES

This Startup Beat Gemini 3 on ARC-AGI — at Half the Cost

Artie: Real Time Data Streaming For The AI Age

The Future of AI Molecular Discovery

Lessons from Building Open Source Libraries

A New Approach To AI Models

The End of the Designer–Engineer Divide