Skip to main content
Open Memory Protocol (OMP) gives your AI application one consistent API for storing, searching, and retrieving memory — regardless of which backend powers it. Write your code once against Memory.add(), Memory.search(), and Memory.context(), then swap between Postgres, Mem0, Supermemory, or Letta with a single line change.

Quick Start

Run your first memory operation in under 5 minutes using the Postgres backend.

Installation

Install the openmem package with the extras for your chosen provider.

Core Concepts

Understand memories, scopes, providers, and context blocks.

API Reference

Full HTTP endpoint reference with request and response schemas.

​
How it works

OMP sits between your application and any memory backend. You call the same Python methods (or HTTP routes) regardless of which provider you choose. The SDK automatically detects whether a provider speaks OMP natively and selects the right adapter for you.
1

Install the SDK

2

Connect to a provider

3

Add and search memories

4

Inject context into LLM prompts

​
Supported providers

Switch providers

Learn how to change backends with zero application code changes.

Async usage

Use AsyncMemory for non-blocking memory operations in async apps.

LLM integration

Inject ranked, citation-tagged memory into any LLM prompt.

HTTP server

Run omp-server to expose OMP over HTTP for any language or framework.