Open protocol and SDKs that connect AI apps to tools and data.
Mem0
Memory layer for AI agents and assistants.
SharkScore
#26 in Frameworks & SDKs
Why it scores 70.1
Mem0 has a SharkScore of 70.1/100, ranked #26 of 665 in Frameworks & SDKs (updated 2026-11-18).
Each part compares Mem0 with other listings in Frameworks & SDKs. Evidence covers 87% of the score's weight.
- Adoption
- 52 · 30%
- User reviews
- no data · 25%
- Maintenance
- 100 · 20%
- Trust & transparency
- 80 · 15%
- Momentum
- no data · 10%
Paying never changes this score. How ranking works · method v2026-11-18.2
RankShark review of Mem0
Automated evaluation by RankShark · 18 Nov 2026 · method v1.0 · How we review
We were not paid for this review.
As of 2026-11-18, Mem0 is a persistent-memory layer for AI agents and apps; its free plan has monthly request caps, while paid pricing is custom. [E2][E3]
Mem0 provides long-term memory for AI agents and applications, so they can save and search information across sessions, tools, and runs. It offers a hosted service and an open-source version for running on your own servers. [E3]
Best for
Not for
- Teams that need a published fixed price for a paid plan; the pricing page lists a Custom plan and asks customers to contact Mem0. · pricing page
Key features
- Persistent memory. The vendor says memory persists across sessions, tools, and runs. · docs
- Memory extraction and retrieval. The vendor says Mem0 extracts and updates memories, then retrieves key memories as users interact. · home page
- Memory compression. The vendor says its Memory Compression Engine condenses chat history into compact memories. · home page
- Framework guides. The vendor says it provides setup guides for 22 tools, including LangChain, CrewAI, LlamaIndex, and the Vercel AI SDK. · docs
- Self-hosting. The vendor says the open-source version can run as a library or Docker stack on the customer's infrastructure. · docs
- Custom-plan features. The vendor lists graph memory, user profiles, memory consolidation, advanced analytics, SSO, audit logs, and on-prem deployment for its Custom plan. · pricing page
Pros
- The free plan includes unlimited end users and published request allowances. · pricing page
- The documentation describes framework setup guides and Python or JavaScript quickstarts. · docs
- An open-source version is documented for running on the customer's own infrastructure. · docs
Cons
- The pricing page does not give a numeric price for the Custom plan. · pricing page
- The Free plan's Mem0-provided model calls are listed for the first 30 days; afterward the page specifies using your own LLM key. · pricing page
- The privacy policy says information from Free Plan users' interactions is used to train AI models; it says Paid Plan user data is not used for that training. · privacy page
Pricing
| Plan | Price | Limits |
|---|---|---|
| Free | Free | Unlimited end users. First 30 days: 10,000 adds and 1,000 retrievals a month, model calls on Mem0. With your own LLM key: 50,000 adds and 10,000 retrievals a month. Usage-based billing past your limits, with a monthly cap you set. |
| Custom | Custom | Limits set to your volume. The page lists graph memory, user profiles, Dream (memory consolidation), advanced analytics, private Slack support, SSO, audit logs and SLA, on-prem deployment, and custom integrations. |
Checked 18 Nov 2026 · source
- Free plan
- Free plan with unlimited end users. For the first 30 days, 10,000 adds and 1,000 retrievals per month with model calls on Mem0; with your own LLM key, 50,000 adds and 10,000 retrievals per month. Usage beyond limits is billed by usage, with a monthly cap you set. · pricing page
- Free trial
- Not stated (checked 18 Nov 2026)
- Trains on customer data
- The privacy policy says information from Free Plan users' interactions is used to train AI models and for other machine-learning purposes. It says Mem0 does not train its AI models on Paid Plan users' data. · privacy page
- Data retention
- The privacy policy says personal information is kept only as long as necessary for the purposes described in that policy. · privacy page
- Data regions
- Not stated (checked 18 Nov 2026)
- Data processing agreement
- The privacy policy says processing on behalf of business customers may be governed by customer agreements, including a Data Processing Addendum. · privacy page
- AI models used
- Not stated (checked 18 Nov 2026)
- API
- Not stated (checked 18 Nov 2026)
- SDKs
- The vendor documents Python and JavaScript quickstarts and says the service includes software development kits. · home page, docs, terms
- Webhooks
- Not stated (checked 18 Nov 2026)
- Platforms
- The vendor documents Python and JavaScript quickstarts and says the open-source version can run as a library or Docker stack on the customer's infrastructure. · docs
What we measured
- GitHub stars · now
- 69,150
- Latest release · now
- ts-v3.3.1 on 2026-09-25
- Package downloads · 30 days
- 3,520,495
- Tranco traffic rank · list of the day
- #145,084
How we tested · sources
- Hourly uptime and response-time checks of the product's URL.
- Repository, release and download data from GitHub, npm, PyPI and Hugging Face where they exist.
- We did not sign up, pay, or use the product as a customer.
- home page: https://mem0.ai/ · fetched 18 Nov 2026
- pricing page: https://mem0.ai/pricing · fetched 18 Nov 2026
- docs: https://docs.mem0.ai/introduction · fetched 18 Nov 2026
- privacy page: https://mem0.ai/privacy-policy · fetched 18 Nov 2026
- terms: https://mem0.ai/terms · fetched 18 Nov 2026
- security page: https://trust.mem0.ai/ · fetched 18 Nov 2026
Something wrong? Report an error with a public link that shows it; corrections re-run the review.
Top alternatives to Mem0
See all- 81.3ToolOpen source
- 77.7
TypeScript toolkit for building AI apps and agents.
ToolOpen source - 77.7
Build agents and LLM apps in Python and TypeScript.
ToolOpen source - 76.9
Tracing, evaluation and monitoring for LLM apps.
ToolFreemium · from $39/mo