Home / Directory / Agents & orchestration / AI agent memory / Mem0
Mem0
Memory layer for AI agents and apps from Y Combinator's Summer 2024 batch, with an open-source library and a hosted platform that stores and retrieves user memories.
Developers adding long-term user memory to chatbots, copilots, and agents who want a simple add-and-search API with an open-source fallback.
Teams that need graph memory on a small budget, or enterprises that want unified business data and governance more than conversational memory.
Verdict
Mem0 is worth using for developers who want to give an agent persistent memory with a few lines of code. Its large open-source community and simple API make it a safe first choice for this category. Teams that need graph memory should budget for the $249 Pro plan.
Score Breakdown
How Mem0 scores in the categories that matter to its buyers.
Pricing
Mem0 publishes request-based plan prices and offers usage-based pricing on request. An open-source version is also available on GitHub.
| Plan | Price | What stands out |
|---|---|---|
| Hobby | Free | 10,000 add requests and 1,000 retrieval requests a month, 1 project |
| Starter | $19 / month | 50,000 add requests and 5,000 retrieval requests a month |
| Pro | $249 / month | 500,000 adds, 50,000 retrievals, unlimited projects, graph memory, private Slack support |
| Enterprise | Custom | Unlimited requests, on-prem deployment, audit logs, SSO, SLA |
The Field at a Glance
How Mem0 compares with other AI agent memory vendors we reviewed, by Overall Score and relative typical engagement cost.
Mem0 scores 8.0 in AI agent memory, ahead of Zep (7.9), Letta (7.8), Supermemory (7.8), and Cognee (7.7). Relative cost lands mid-band for this subcategory.
Use-case matrix
| Use case | Fit | Notes |
|---|---|---|
| Add and search API | Strong | A few SDK calls store and retrieve user memories. |
| Open-source option | Strong | The library has more than 67,000 GitHub stars. |
| Compliance | Strong | SOC 2 Type I, HIPAA, and GDPR claims on the platform. |
| Graph memory | Mixed | Entity-linking graph memory starts on Pro. |
| Business data unification | Mixed | Focused on user and agent memory more than company data. |
| Air-gapped deployment | Mixed | On-prem deployment is Enterprise only. |
Who it’s for
Good fit
- Chatbot and copilot builders
- AI companion and coaching apps
- Startups wanting an open-source fallback
Poor fit
- Teams needing graph memory cheaply
- Buyers wanting company-wide knowledge graphs
- Projects with no repeat users
Review Excerpts
Below are excerpts from public reviews. Our team scoured public reviews, forums, and chat rooms to get a balanced view of customers' experience with this company. Paid reviews and pay-for-play sites such as Clutch were excluded.
Mem0 says more than 150,000 developers build with it, and its quick start stores and searches a user's memories in a few lines of Python or Node.js.
Mem0's open-source repository shows more than 67,000 GitHub stars, and the hosted platform is listed as SOC 2 Type I, HIPAA, and GDPR compliant.
Mem0's graph memory and memory consolidation are only on Pro at $249 a month, a jump from the $19 Starter plan, and on-prem deployment and SSO are Enterprise only.
Company Facts
- Founded
- 2023 (Y Combinator)
- Headquarters
- San Francisco (Y Combinator)
- Employees
- About 10 (Y Combinator)
- Total funding raised
- $24M (TechCrunch)
- Key investors
- Basis Set Ventures, Kindred Ventures, Y Combinator, Peak XV Partners, GitHub Fund (TechCrunch)
- Accelerator
- Y Combinator, Summer 2024 batch (Y Combinator)
- Website
- mem0.ai
Key Leadership
Taranjeet Singh
Co-founder and CEO
Methodology
This page is an independent evaluation of Mem0 for buyers comparing options in AI agent memory. AI Industry Reviews accepts no sponsorships, advertising, or pay-for-placement fees. Mem0 did not pay for this review.
What we scored
The headline number is an Overall Score on a 0-10 scale. Eight criteria sit under it in two groups.
- Buyer outcomes (for AI agent memory)
- Drop-in memory API
- Open-source adoption
- Graph memory on lower tiers
- Enterprise compliance
- Company & commercial
- Innovation & product leadership
- Project management & communication
- Pricing
- Contract fairness
Pricing measures whether the price looks fair for the value delivered, including packaging and renewal friction that show up in real buying cycles.
Score Composition
| Input | Weight | What it covers |
|---|---|---|
| Reviews | 40% | A proprietary read of what practitioners say about likes, complaints, and day-to-day use, including public review sites, forums, and private chat rooms. Paid reviews and pay-for-play sites such as Clutch are out of scope. |
| Product | 35% | Hands-on look at screens and workflows. |
| Pricing | 15% | Whether the price looks fair for what you get. |
| Docs & training | 10% | Docs, tutorials, and training material. |
How we balanced the evidence
The Overall Score is the simple average of the eight criteria. Recommendation language follows that score and the fit pattern described above.
Scope
Mem0 is graded here as AI agent memory. Criteria scores can move as more review volume and product checks are added.