AutoMind OS

AutoMind OS is an AI-powered automotive diagnostic system designed to assist qualified mechanics in identifying vehicle faults. Built for the 2026 production cycle, it integrates OBD2 scanning, probabilistic fault analysis, and public automotive databases to provide accurate, safe, and data-driven diagnostic hypotheses.

Features

• Probabilistic Fault Analysis: Utilizes a Bayesian inference engine to calculate the probability of various fault hypotheses based on DTCs, live data, and technician complaints.
• AI-Powered Diagnostics: Integrates with OpenAI models to provide a secondary, independent layer of analysis and recommendations.
• OBD2 ELM327 Support: Connects directly to ELM327 adapters for real-time data acquisition (strictly read-only mode for safety).
• Public Data Integration: Seamlessly pulls vehicle intelligence from NHTSA (VIN decoding, recalls, complaints), EU Safety Gate, and UK recall checkers.
• Diagnostic Sessions: Manages the entire diagnostic lifecycle, from vehicle profiling and complaint logging to final report generation.
• Safety First: Hardcoded safety policies block dangerous operations like active tests, coding, or ECU flashing in production builds.
• Built-in Simulator: Includes a robust simulator for testing and development without needing a physical vehicle or OBD adapter.

Architecture

The system is built with a clean, layered architecture using Python 3.11+ and FastAPI:

Layer	Description
Domain	Core data models (Vehicle, Complaint, DTC, LiveData, Hypothesis).
Core	Bayesian inference engine, safety policies, system self-checks, and audit logging.
Services	Business logic for managing diagnostic sessions and generating HTML reports.
Repositories	SQLite database integration for persistent session storage.
Adapters	Hardware and API adapters for ELM327 serial communication and OpenAI.
API	RESTful API (v3) providing endpoints for sessions, public data, and AI analysis.
Integrations	Connectors for NHTSA vPIC, EU Safety Gate, and OEM data import specifications.

Installation & Usage

Prerequisites

• Python 3.11 or newer
• ELM327 OBD2 Adapter (optional, simulator can be used)
• OpenAI API Key (optional, for AI analysis layer)

Setup

1. Clone the repository:

   git clone https://github.com/edik40288-stack/AutoMind_OS.git
   cd AutoMind_OS

2. Install dependencies:

   pip install -r requirements.txt

3. Configure environment variables (copy .env.example to .env and update if needed):

   AI_ENABLED=true
   OPENAI_API_KEY=your_api_key_here
   READ_ONLY=true

Running the System

You can start the diagnostic server using the provided batch or PowerShell scripts:

./START_AUTODIAG.bat
# or
./START_AUTODIAG.ps1

Once running, access the web interface at http://127.0.0.1:8765.

Safety & Limitations

AutoMind OS is designed to operate in read-only mode by default. The safety policy (app/core/safety.py) strictly prevents clearing DTCs, running active tests, coding, or flashing ECUs to ensure the safety of both the technician and the vehicle.

While it includes public data from NHTSA and other sources, it does not contain proprietary OEM databases (UDS descriptions, wiring diagrams, or guided functions), which require separate licensed integrations for full vehicle coverage.

Tech Stack

• Language: Python
• Backend: FastAPI
• Database: SQLite
• Hardware: ELM327 (via Serial)
• Frontend: HTML/CSS/JavaScript

License

This project is licensed under the MIT License.