Skip to main content

​
Mem0 Open Source Overview

Mem0 Open Source delivers the same adaptive memory engine as the platform, but packaged for teams that need to run everything on their own infrastructure. You own the stack, the data, and the customizations.
Mem0 v1.0.0 brought rerankers, async-by-default clients, and Azure OpenAI support. See the release notes for the full rundown before upgrading.

​
What Mem0 OSS provides

  • Full control: Tune every component, from LLMs to vector stores, inside your environment.
  • Offline ready: Keep memory on your own network when compliance or privacy demands it.
  • Extendable codebase: Fork the repo, add providers, and ship custom automations.
Begin with the Python quickstart (or the Node.js variant) to clone the repo, configure dependencies, and validate memory reads/writes locally.

​
Choose your path

Python Quickstart

Bootstrap CLI and verify add/search loop.

Node.js Quickstart

Install TypeScript SDK and run starter script.

Configure Components

LLM, embedder, vector store, reranker setup.

Graph Memory Capability

Relationship-aware recall with Neo4j, Memgraph.

Tune Retrieval & Rerankers

Hybrid retrieval and reranker controls.

Deploy with Docker Compose

Reference deployment with REST endpoints.

Use the REST API

Async add/search flows and automation.
Need a managed alternative? Compare hosting models in the Platform vs OSS guide or switch tabs to the Platform documentation.
BenefitWhat you get
Full infrastructure controlHost on your own servers with complete access to configuration and deployment.
Complete customizationModify the implementation, extend functionality, and tailor it to your stack.
Local developmentPerfect for development, testing, and offline environments.
No vendor lock-inKeep ownership of your data, providers, and pipelines.
Community drivenContribute improvements and tap into a growing ecosystem.

​
Default components

Mem0 OSS works out of the box with sensible defaults:
  • LLM: OpenAI gpt-4.1-nano-2025-04-14 (via OPENAI_API_KEY)
  • Embeddings: OpenAI text-embedding-3-small
  • Vector store: Local Qdrant instance storing data at /tmp/qdrant
  • History store: SQLite database at ~/.mem0/history.db
  • Reranker: Disabled until you configure a provider
Override any component with Memory.from_config.

​
Keep going

Review Platform vs OSS

Run the Python Quickstart

Need a managed alternative? Compare hosting models in the Platform vs OSS guide or switch tabs to the Platform documentation.