Mem0: Memory Layer

Founded 2023|San Francisco, CA|11-50 people|Freemium

What is Mem0?

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.

Key features

Core capabilities this platform advertises.

Long-term memory for AI agents
Automatic memory extraction from conversations
User-level and session-level memory
Framework integrations
Memory search and retrieval API

Strengths and tradeoffs

What this tool does well, and the limitations to keep in mind.

Pros

Strong backing: USD 24M from top VCs including YC and Peak XV
80,000+ developers and AWS Agent SDK exclusive provider
Free tier with 10,000 memories enables thorough evaluation
Both cloud and self-hosted deployment options

Cons

Graph memory only on expensive USD 249/month Pro plan
Significant price jump from USD 19 to USD 249 for advanced features
Relatively new company (2023) with limited long-term track record
Free tier 1,000 retrieval calls may be restrictive for evaluation

Plans & pricing

What's included in each plan, and how the tiers compare.

Free

10,000 memories
1,000 retrieval calls/month
Vector memory
Cloud hosted
Community support

Pro Starter

$19

Per month

50,000 memories
Unlimited retrieval
Vector memory
Email support

Pro

$249

Per month

Unlimited memories
Graph memory
Advanced features
Priority support

Enterprise

Custom

Contact sales for a quote

Self-hosted option
Custom integrations
SLA guarantees
Dedicated support

View official pricing page

Common use cases

Developers building AI agents that need to remember user context across sessions

Personalized AI assistants that remember users
Agent learning from past interactions
Customer support with conversation history
AI companions with persistent memory
Multi-session context continuity

Using Mem0 with Respan

Mem0 and Respan enable persistent AI memory with monitoring. Add memory to AI apps with Mem0 while tracking costs with Respan.

Monitor Mem0 API costs for memory storage and retrieval
Track memory usage patterns and retrieval effectiveness
Debug memory-related issues using Respan execution traces
Optimize memory architecture based on Respan usage analytics

Run Mem0 in production with Respan

10KFree traces/mo

1,000+Models

5 minSetup

Respan lets you trace LLM and agent calls across any model or framework, A/B test prompts on production traffic, and route requests across 1,000+ models through one gateway.

Try Respan free