Skip to main content
Mem0 v1.0.0 is now available — Introducing rerankers, async by default, Azure support, and more. View changelog →

​
Self-Host Mem0 with Full Control

Mem0 Open Source gives you a powerful, self-hosted memory layer for AI agents. Deploy on your infrastructure, customize every component, and maintain complete data ownership.

​
Get Started

Choose your preferred SDK and get Mem0 running locally in minutes:

Python Quickstart

Install and configure Mem0 OSS with Python in 10 minutes

Node.js Quickstart

Set up Mem0 OSS with Node.js and TypeScript support

​
Explore OSS Capabilities

Mem0 Open Source offers powerful features for building production-grade AI applications with memory. From graph-based knowledge structures to flexible component configuration, you have full control over how memory works in your system.

Graph Memory

Build relationship-aware memory with knowledge graph capabilities

Component Configuration

Choose your LLM, vector database, embedding model, and rerankers

REST API

Build high-throughput pipelines with async clients and REST endpoints
Platform vs OSS? See our comparison guide to understand which deployment option fits your use case.

​
Why Choose Open Source?

BenefitWhat You Get
Full Infrastructure ControlHost on your own servers with complete access to configuration and deployment
Complete CustomizationModify implementation, extend functionality, and adapt to your specific needs
Local DevelopmentPerfect for development, testing, and air-gapped environments
No Vendor Lock-inOwn your data, choose your stack, and maintain full independence
Community DrivenContribute to and benefit from active community improvements and integrations
Looking for production scale? Mem0 Platform offers managed infrastructure with advanced features like webhooks, multimodal support, and enterprise support.
Need help? Check out our GitHub repository for source code, issues, and community discussions.

​
Default Components

No configuration needed to get started. Mem0 works out of the box with sensible defaults:
  • LLM: OpenAI gpt-4.1-nano-2025-04-14 via your OPENAI_API_KEY
  • Embeddings: OpenAI text-embedding-3-small (1536 dimensions)
  • Vector store: Local Qdrant instance storing data at /tmp/qdrant
  • History storage: SQLite database at ~/.mem0/history.db
  • Reranker: Disabled unless you configure one
Override any component with Memory.from_config.
⌘I