🧠 myBrAIn — MCP Ecosystem

Deterministic, Idempotent, Context-Aware Second Brain for Google Antigravity.

---

Introduction

myBrAIn is an MCP (Model Context Protocol) server designed to provide persistent and contextual memory to language models (like Google Antigravity). It acts as a “second brain” for your development environment, allowing the AI to remember project rules, architectural decisions, and technical insights across different chat sessions.

---

System Architecture

The system is divided into three main components:

• Core: Manages persistence (db.py) and analytical intelligence (analyzer.py) for extracting insights from code.
• Server: The standard MCP interface (server.py) that allows Antigravity to interact with the brain.
• Admin UI: A premium dashboard (admin.py) based on Streamlit to visualize, manage, and debug stored memories with advanced features like Knowledge Graphs, Memory Export, and the Silent Observer dashboard.
• Observer: A background daemon thread (observer.py) that monitors codebase drift in real-time.

---

🏗 Installation

A. Docker Deployment (Recommended)

The easiest way to run myBrAIn is using Docker Compose.

# Clone & Prepare
git clone https://github.com/lilium360/myBrAIn.git
cd myBrAIn
cp .env.example .env

# Spin up
docker compose up -d

The Admin UI will be available at: http://localhost:8501

B. Local Installation (Native Python)

1. Clone & Enter:

   git clone https://github.com/lilium360/myBrAIn.git
   cd myBrAIn
   

2. Setup Environment:
   • Windows: python -m venv venv && .\venv\Scripts\activate
   • Unix: python3 -m venv venv && source venv/bin/activate
3. Install: pip install -r requirements.txt

---

🚀 Usage Guide

1. Launching the Admin Dashboard

To graphically manage the database and visualize insights:

• Via Docker: Already running after docker compose up. Open http://localhost:8501.
• Via Python: Run streamlit run admin.py (or python -m streamlit run admin.py).

2. Integration in IDEs (Cursor, VS Code + Antigravity)

Add this to your mcpServers configuration JSON:

Option A: Via Docker

{
  "mcpServers": {
    "mybrain": {
      "command": "docker",
      "args": ["exec", "-i", "mybrain-admin", "python", "server.py"],
      "env": {
        "MYBRAIN_DATA_DIR": "/data/mybrain"
      }
    }
  }
}

Option B: Via Python (Local)

{