t6_mem0_v2/README.md

T6 Mem0 v2 - Memory System for LLM Applications

Comprehensive memory system based on mem0.ai featuring MCP server integration, REST API, hybrid storage architecture, and AI-powered memory management.

Features

• MCP Server: HTTP/SSE and stdio transports for universal AI integration
  • ✅ n8n AI Agent workflows
  • ✅ Claude Code integration
  • ✅ 7 memory tools (add, search, get, update, delete)
• REST API: Full HTTP API for memory operations (CRUD)
• Hybrid Storage: Supabase (pgvector) + Neo4j (graph relationships)
• Synchronized Operations: Automatic sync across vector and graph stores
• Flexible LLM Support:
  • ✅ OpenAI (GPT-4, GPT-3.5)
  • ✅ Ollama (Llama 3.1, Mistral, local models)
  • ✅ Switchable via environment variables
• Multi-Agent Support: User and agent-specific memory isolation
• Graph Visualization: Neo4j Browser for relationship exploration
• Docker-Native: Fully containerized with Docker Compose

Architecture

Clients (n8n, Claude Code, Custom Apps)
    ↓
┌─────────────────┬───────────────────┐
│ MCP Server      │ REST API          │
│ Port 8765       │ Port 8080         │
│ HTTP/SSE+stdio  │ FastAPI           │
└─────────────────┴───────────────────┘
    ↓
Mem0 Core Library (v1.0.0)
    ↓
┌─────────────────┬───────────────────┬──────────────────────┐
│ Supabase        │ Neo4j 5.28+       │ OpenAI / Ollama      │
│ Vector Store    │ Graph Store       │ Embeddings+LLM       │
│ pgvector        │ Cypher Queries    │ Async by default     │
└─────────────────┴───────────────────┴──────────────────────┘

Quick Start

Prerequisites

• Docker and Docker Compose
• Existing Supabase instance (PostgreSQL with pgvector)
• Choose one:
  • OpenAI API key (for cloud LLM)
  • Ollama installed (for local LLM) - Setup Guide
• Python 3.11+ (for development)

Installation

# Clone repository
git clone https://git.colsys.tech/klas/t6_mem0_v2
cd t6_mem0_v2

# Configure environment
cp .env.example .env
# Edit .env with your credentials

# Start services
docker compose up -d

# Verify health
curl http://localhost:8080/v1/health
curl http://localhost:8765/health

Configuration

Create .env file:

Option 1: OpenAI (Default)

# LLM Configuration
LLM_PROVIDER=openai
EMBEDDER_PROVIDER=openai
OPENAI_API_KEY=sk-your-key-here

# Supabase
SUPABASE_CONNECTION_STRING=postgresql://user:pass@172.21.0.12:5432/postgres

# Neo4j
NEO4J_URI=neo4j://neo4j:7687
NEO4J_USER=neo4j
NEO4J_PASSWORD=your-password

# REST API
API_KEY=your-secure-api-key

# MCP Server
MCP_HOST=0.0.0.0
MCP_PORT=8765

# Mem0 Configuration
MEM0_COLLECTION_NAME=t6_memories
MEM0_EMBEDDING_DIMS=1536  # OpenAI embeddings
MEM0_VERSION=v1.1

Option 2: Ollama (Local LLM)

# LLM Configuration
LLM_PROVIDER=ollama
EMBEDDER_PROVIDER=ollama
OLLAMA_BASE_URL=http://localhost:11434
OLLAMA_LLM_MODEL=llama3.1:8b
OLLAMA_EMBEDDING_MODEL=nomic-embed-text

# Supabase
SUPABASE_CONNECTION_STRING=postgresql://user:pass@172.21.0.12:5432/postgres

# Neo4j
NEO4J_URI=neo4j://neo4j:7687
NEO4J_USER=neo4j
NEO4J_PASSWORD=your-password

# REST API
API_KEY=your-secure-api-key

# MCP Server
MCP_HOST=0.0.0.0
MCP_PORT=8765

# Mem0 Configuration
MEM0_COLLECTION_NAME=t6_memories
MEM0_EMBEDDING_DIMS=768  # Ollama nomic-embed-text
MEM0_VERSION=v1.1

See Ollama Setup Guide for detailed configuration.

Usage

REST API

# Add memory
curl -X POST http://localhost:8080/v1/memories/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"messages":[{"role":"user","content":"I love pizza"}],"user_id":"alice"}'

# Search memories
curl -X GET "http://localhost:8080/v1/memories/search?query=food&user_id=alice" \
  -H "Authorization: Bearer YOUR_API_KEY"

MCP Server

HTTP/SSE Transport (for n8n, web clients):

# MCP endpoint
http://localhost:8765/mcp

# Test tools/list
curl -X POST http://localhost:8765/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'

stdio Transport (for Claude Code, local tools):

Add to ~/.config/claude/mcp.json:

{
  "mcpServers": {
    "t6-mem0": {
      "command": "python",
      "args": ["-m", "mcp_server.main"],
      "cwd": "/path/to/t6_mem0_v2",
      "env": {
        "OPENAI_API_KEY": "${OPENAI_API_KEY}",
        "SUPABASE_CONNECTION_STRING": "${SUPABASE_CONNECTION_STRING}",
        "NEO4J_URI": "neo4j://localhost:7687",
        "NEO4J_USER": "neo4j",
        "NEO4J_PASSWORD": "${NEO4J_PASSWORD}"
      }
    }
  }
}

n8n Integration:

Use the MCP Client Tool node in n8n AI Agent workflows:

{
  "endpointUrl": "http://172.21.0.14:8765/mcp",  // Use Docker network IP
  "serverTransport": "httpStreamable",
  "authentication": "none",
  "include": "all"
}

See n8n integration guide for complete workflow examples.

Documentation

Full documentation available at: docs/ (Mintlify)

MCP Server

• MCP Server Introduction
• MCP Installation Guide
• MCP Tool Reference

Integration Guides

• n8n Integration Guide
• Claude Code Integration

Setup

• Ollama Setup (Local LLM)

Architecture

• Architecture Overview
• Project Requirements

Project Structure

t6_mem0_v2/
├── api/                    # REST API (FastAPI)
│   ├── main.py            # API entry point
│   ├── memory_service.py  # Memory operations
│   └── routes.py          # API endpoints
├── mcp_server/            # MCP server implementation
│   ├── main.py           # stdio transport (Claude Code)
│   ├── http_server.py    # HTTP/SSE transport (n8n, web)
│   ├── tools.py          # MCP tool definitions
│   └── server.py         # Core MCP server logic
├── docker/                # Docker configurations
│   ├── Dockerfile.api    # REST API container
│   └── Dockerfile.mcp    # MCP server container
├── docs/                  # Mintlify documentation
│   ├── mcp/              # MCP server docs
│   └── examples/         # Integration examples
├── tests/                 # Test suites
├── config.py             # Configuration management
├── requirements.txt      # Python dependencies
└── docker-compose.yml    # Service orchestration

Technology Stack

• Core: mem0ai library v1.0.0 (async by default, v1.1 API)
• Vector DB: Supabase with pgvector
• Graph DB: Neo4j 5.28+
• LLM Options:
  • OpenAI API (GPT-4o-mini, text-embedding-3-small)
  • Ollama (Llama 3.1, Mistral, nomic-embed-text)
• REST API: FastAPI
• MCP: Python MCP SDK
• Container: Docker & Docker Compose

Roadmap

Phase 1: Foundation ✅ COMPLETED

• ✅ Architecture design
• ✅ REST API implementation (FastAPI with Bearer auth)
• ✅ MCP server implementation (HTTP/SSE + stdio transports)
• ✅ Supabase integration (pgvector for embeddings)
• ✅ Neo4j integration (graph relationships)
• ✅ Documentation site (Mintlify)
• ✅ n8n AI Agent integration
• ✅ Claude Code integration
• ✅ Docker deployment with health checks

Phase 2: Local LLM ✅ COMPLETED

• ✅ Local Ollama integration
• ✅ Model switching capabilities (OpenAI ↔ Ollama)
• ✅ Embedding model selection
• ✅ Environment-based provider configuration

Phase 3: Advanced Features

• ⏳ Memory versioning and history
• ⏳ Advanced graph queries and analytics
• ⏳ Multi-modal memory support (images, audio)
• ⏳ Analytics dashboard
• ⏳ Memory export/import
• ⏳ Custom embedding models

Development

# Install dependencies
pip install -r requirements.txt

# Run tests
pytest tests/

# Format code
black .
ruff check .

# Run locally (development)
python -m api.main

Contributing

This is a private project. For issues or suggestions, contact the maintainer.

License

Proprietary - All rights reserved

Support

• Repository: https://git.colsys.tech/klas/t6_mem0_v2
• Documentation: See docs/ directory
• Issues: Contact maintainer

---

Status: Phase 2 Complete - Production Ready with Ollama Support Version: 1.2.0 Last Updated: 2025-10-16

Recent Updates

• 2025-10-16: ✅ Upgraded to mem0ai v1.0.0 (async by default, v1.1 API, improved retrieval)
• 2025-10-16: ✅ Updated Neo4j to 5.28+ (required by langchain-memgraph)
• 2025-10-16: ✅ Removed OpenAI version upper limit (now supports OpenAI 2.x)
• 2025-10-16: ✅ Fixed timezone configuration (Europe/Prague)
• 2025-10-16: ✅ Fixed mem0 library hardcoded US/Pacific timezone
• 2025-10-16: ✅ Added missing ollama Python library dependency
• 2025-10-16: ✅ Added Ollama test scripts for configuration validation
• 2025-10-15: ✅ Ollama integration complete - local LLM support
• 2025-10-15: ✅ Flexible provider switching (OpenAI ↔ Ollama)
• 2025-10-15: ✅ Support for multiple embedding models
• 2025-10-15: MCP HTTP/SSE server implementation complete
• 2025-10-15: n8n AI Agent integration tested and documented
• 2025-10-15: Complete Mintlify documentation site
• 2025-10-15: Synchronized delete operations across stores
• 2025-10-13: Initial project setup and architecture