# T6 Mem0 v2 - Project Requirements

## Original User Request

**Date**: 2025-10-13

### Core Objectives

Set up a comprehensive memory system with the following capabilities:
- **MCP Server Integration**: Serve as an MCP server for Claude and other LLM-based systems
- **REST API Access**: Enable memory storage and retrieval via REST API
- **Data Storage**: Use locally running Supabase for primary data storage
- **Graph Visualization**: Use Neo4j for storing and visualizing memory relationships
- **LLM Integration**: Initial phase with OpenAI, future phase with local Ollama instance

### Technology Stack

**Phase 1 (Initial Implementation)**:
- mem0.ai as the core memory framework
- Supabase (local instance) for vector and structured storage
- Neo4j for graph-based memory relationships
- OpenAI API for embeddings and LLM capabilities
- MCP (Model Context Protocol) server for AI agent integration

**Phase 2 (Future)**:
- Local Ollama integration for LLM independence
- Additional local model support

### Key Requirements

1. **MCP Server**: Must function as an MCP server that can be used by Claude Code and other LLM systems
2. **REST API**: Full REST API for CRUD operations on memories
3. **Local Infrastructure**: All data storage must be local (Supabase, Neo4j)
4. **Visualization**: Neo4j integration for memory graph visualization
5. **Documentation**: Mintlify-based documentation site
6. **Version Control**: Git repository at https://git.colsys.tech/klas/t6_mem0_v2

### Repository Information

- **Git Remote**: https://git.colsys.tech/klas/t6_mem0_v2
- **Username**: klas
- **Password**: csjXgew3In

### Project Phases

#### Phase 1: Foundation
- Research and validate mem0.ai capabilities
- Design architecture with Supabase + Neo4j + OpenAI
- Implement core memory storage and retrieval
- Build MCP server interface
- Create REST API endpoints
- Set up Mintlify documentation

#### Phase 2: Local LLM Integration
- Integrate Ollama for local model support
- Add model switching capabilities
- Performance optimization for local models

### Success Criteria

- Functional MCP server that Claude Code can use
- Working REST API for memory operations
- Memories persisted in local Supabase
- Graph relationships visible in Neo4j
- Complete documentation in Mintlify
- All code versioned in git repository