Description
Mem0 is a memory layer for AI agents and applications. It adds persistent, searchable memory, so an assistant can remember user preferences and past interactions across sessions without changes to your pipeline. You add memories with an SDK for Python or Node.js, and the system learns from them and retrieves relevant context when you need it. The site lists a Memory Compression Engine, graph memory that links entities, and memory consolidation for longer-running agents. Setup is available for agents through an agent harness or plugin, and there are domain examples for healthcare and therapy assistants. The project is open source on GitHub, with releases and a Discord community, and the site reports more than 60,000 stars. The Hobby plan is free, with 10,000 add requests and 1,000 retrieval requests a month and one project. The Starter plan costs $19 a month, and the Pro plan costs $249 a month, with graph memory, advanced analytics and private Slack support.…
Preview
Pricing
- HobbyFree
- Starter$19/mo
- Pro$249/mo
Highlights
- Persistent memory across sessions
- Python and Node.js SDKs
- Graph memory and memory compression
- Agent harness and plugin setup
- Open source on GitHub
Ratings & Reviews
No ratings yet
Be the first to rate Mem0.
People also visit
Mem0 FAQ
What is Mem0?
A memory layer that gives AI agents and apps persistent, searchable memory across sessions.
Is there a free plan?
Yes. The Hobby plan is free, with 10,000 add requests and 1,000 retrieval requests a month and one project.
How much do the paid plans cost?
Starter is $19 a month with 50,000 add requests. Pro is $249 a month with 500,000 add requests, unlimited projects and graph memory.
How do I add it to my app?
Install the mem0ai SDK for Python or Node.js, then add and search memories using a user ID.
Is it open source?
Yes. The code is on GitHub under mem0ai.
What are the best Mem0 alternatives?
Popular alternatives to Mem0 include MemOS, MemMachine and GrayMatter. See all Mem0 alternatives

