# Mem0

> Open-source memory layer that lets AI agents store, compress and recall user context across sessions

Source: https://dontaskagain.com/mem0
Website: https://mem0.ai/?utm_source=dontaskagain
Pricing: Freemium
Categories: [Memory](https://dontaskagain.com/categories/memory.md), [Open source](https://dontaskagain.com/categories/open-source.md)
Listed: 2026-10-18
Updated: 2026-10-18

Mem0 is a memory layer that lets developers' AI agents and apps remember users across sessions and agents. Apps send conversations or other data through the SDK, Mem0 extracts and updates the facts worth keeping, and the agent retrieves relevant memories later, such as dietary restrictions or past preferences, without pipeline changes.

**Key features:**

- Add memories from conversations and retrieve them by relevance.
- Condense chat history into compact memories to cut tokens and latency.
- Link entities with graph memory and consolidate memories with Dream.
- Integrate through Python and Node.js SDKs, an agent harness setup or plugins.
- Track memory usage with analytics across projects.

The core is open source under Apache 2.0 for self-hosting, alongside the hosted platform. The free Hobby plan includes 10,000 add and 1,000 retrieval requests a month; Starter is $19/month, Pro is $249/month with graph memory, and Enterprise adds on-prem deployment, SSO and audit logs.

## More memory agents

- [Zep](https://dontaskagain.com/zep.md): Context layer that builds governed, time-aware context graphs from business data so agents retrieve what tasks need
- [Letta](https://dontaskagain.com/letta.md): Research lab behind MemGPT building stateful agents with persistent, self-improving memory
- [Supermemory](https://dontaskagain.com/supermemory.md): Memory and continual-learning engine that stores agent context in a time-aware graph and injects it at runtime