Memory & PersistenceOpen Source✦ Free Tier

Mem0

Universal persistent memory layer for AI agents

⭐ 30,000 stars● Health 85/100 — Active· commit recency (40 pts) · star momentum (30 pts) · issue ratio (20 pts) · forks (10 pts)App Infrastructure

Open in Builder →Website ↗GitHub ↗

About

Open-source persistent memory layer that gives AI agents the ability to remember users, preferences, and context across sessions. Supports vector, graph, and key-value storage backends. AWS partner for Strands Agents. YC W23, $24M raised, 30K+ GitHub stars.

Choose Mem0 when…

•You want your AI agent to remember users and preferences across sessions
•You need a universal memory layer that works with any LLM or framework
•You're building personalized AI assistants with long-term context

Builder Slot

How does your AI remember?Optional for most stacks

Persistent memory layers that give AI agents long-term recall of users, sessions, and context across conversations

Dev Tools

Not applicable

App Infra

Optional

Hybrid

Optional

Other tools in this slot:

Zep Cognee Graphiti

Stack Genome Detection

AIchitect's Genome scanner detects Mem0 in your project via these signals:

pip packages

mem0ai

env vars

MEM0_API_KEY

Integrates with (2)

OpenAI APILLM Infrastructure

Mem0 ships first-class OpenAI support — embeddings for retrieval and chat models for fact extraction and summarisation, configured via a single config block.

→ Add long-term memory to OpenAI-based agents without writing custom storage or retrieval logic.

Compare →

QdrantLLM Infrastructure

Mem0 supports Qdrant as a vector store backend for memory embeddings, alongside Chroma, Pinecone, pgvector, and others.

→ Run Mem0 on Qdrant when you want a managed or self-hosted vector backend with metadata filtering.

Compare →