Free
Free
- 10,000 memories
- 1,000 retrieval calls/month
- Vector memory
- Cloud hosted
- Community support
Mem0 is a Y Combinator-backed memory layer for AI applications founded in 2023 by Taranjeet Singh (ex-Khatabook first growth engineer) and Deshraj Yadav (ex-Tesla Autopilot AI Platform lead). Launched in January 2024, Mem0 raised USD 24 million including USD 3.9 million in seed funding and USD 20 million Series A led by Basis Set Ventures, with participation from Kindred Ventures, Y Combinator, Peak XV Partners, and GitHub Fund. The company serves over 80,000 developers and provides the exclusive memory provider for AWS new Agent SDK. Mem0 offers a free tier with 10,000 memories and 1,000 retrieval calls per month, Pro plans at USD 19-249/month with different memory limits, and custom Enterprise pricing. The platform supports both cloud-hosted and self-hosted deployment options. Graph memory capabilities are only available on Pro plans (USD 249/month) or higher. Mem0 specializes in persistent memory for LLM applications, enabling AI systems to remember context across interactions for improved personalization and continuity.
Core capabilities this platform advertises.
What this tool does well, and the limitations to keep in mind.
Pros
Cons
What's included in each plan, and how the tiers compare.
Free
$19
Per month
$249
Per month
Custom
Contact sales for a quote
Developers building AI agents that need to remember user context across sessions
Mem0 and Respan enable persistent AI memory with monitoring. Add memory to AI apps with Mem0 while tracking costs with Respan.
Top companies in Memory Layer you can use instead of Mem0.
Side-by-side comparisons with other tools in this category.
Companies from adjacent layers in the AI stack that work well with Mem0.
Last verified: March 10, 2026