---
title: 'Quickstart'
description: 'Get your Mem0 Memory System running in under 5 minutes'
---
## Prerequisites
Required for Neo4j container (Supabase already running)
For the mem0 core system and API
## Installation
### Step 1: Verify Database Services
Both required database services are already running:
**Neo4j** is already running in Docker container `mem0-neo4j` on ports 7474 (HTTP) and 7687 (Bolt).
**Supabase** is already running as part of your existing infrastructure on the localai network.
You can verify the services are running:
```bash
# Check running containers
docker ps | grep -E "(neo4j|supabase)"
# Test Neo4j connection
curl http://localhost:7474
# Test Supabase connection
curl http://localhost:8000/health
```
### Step 2: Test Your Installation
```bash
python test_all_connections.py
```
You should see all systems passing.
### Step 3: Start the REST API Server ✅
Our Phase 2 implementation provides a production-ready REST API with two deployment options:
For local development and testing:
```bash
python start_api.py
```
**Access:** http://localhost:8080 (localhost only)
For external access and production deployment:
```bash
# Build and start the API server
docker-compose -f docker-compose.api.yml up -d
```
**Access:** http://YOUR_SERVER_IP:8080 (accessible from outside)
The Docker deployment automatically configures the API to accept external connections on `0.0.0.0:8080`.
Both options provide:
- Interactive documentation at `/docs`
- Full authentication and rate limiting
- Comprehensive error handling
### Step 4: Test the API
Run our test suite to verify everything works:
```bash
# Quick validation test
python test_api_simple.py
# Comprehensive test suite
python test_api.py
```