Skip to main content
Mem0 Open Source is the same memory engine as the Platform, running on your own infrastructure. You own the stack, the data, and every component, and you choose where each one runs. Run it two ways:
  • As a library in your app. pip install mem0ai (or npm install mem0ai), call Memory(), and you have memory in a few lines.
  • As a self-hosted server. A Docker stack with a dashboard, per-user API keys, and a request audit log.

​
Get started

Python Quickstart

Install the SDK and verify the add/search loop in a few lines.

Node.js Quickstart

Install the TypeScript SDK and run the starter script.

Self-hosted server

Run make bootstrap to launch the server, dashboard, and your first API key.

​
Go further

Configure components

Set your LLM, embedder, vector store, and reranker.

Self-hosting features

Async memory, metadata filters, reranker search, multimodal, and more.

Build with cookbooks

End-to-end examples: companions, agents, and integrations.
Need a managed alternative? Compare hosting models in the Platform vs OSS guide or switch tabs to the Platform documentation.

​
Default components

Mem0 runs out of the box with the defaults below. Override any of them through configuration. As a library (you import Mem0 and call Memory()):
ComponentDefault
LLMOpenAI gpt-5-mini (set OPENAI_API_KEY)
EmbeddingsOpenAI text-embedding-3-small
Vector storeLocal Qdrant at /tmp/qdrant
History storeSQLite at ~/.mem0/history.db
RerankerDisabled until configured
Override any component with Memory.from_config. As a self-hosted server (the server/ Docker Compose stack):
ComponentDefault
LLMOpenAI gpt-5-mini (override with MEM0_DEFAULT_LLM_MODEL)
EmbeddingsOpenAI text-embedding-3-small (override with MEM0_DEFAULT_EMBEDDER_MODEL)
Vector storePostgres + pgvector
Bundled providersopenai, anthropic, gemini (switch on the Configuration page)
See Self-Hosted Setup for the full provider list and how to extend it.
Using Mem0? Star us on GitHub to help more developers discover memory for AI apps.