SeriousOldMan/Simulator-Controller

A virtual AI-based pit crew for Sim Racing. Use the latest GPT technology to create a real life like experience when out on the track.

What it solves

Simulator Controller is a modular administration and controller application for Sim Racing that reduces the driver's cognitive load by automating cumbersome tasks and providing real-time, AI-driven guidance. It replaces the need for manual hardware control or constant monitoring of weather, strategy, and car handling during a race.

How it works

The system uses a hybrid rule engine combined with voice recognition and synthesis to power several specialized AI Assistants. These assistants can be connected to GPT services (LLMs) to enable more natural, life-like conversations and custom behaviors. The application integrates with external hardware like Button Boxes and Stream Decks to control simulator components (e.g., SimHub, SimFeedback) and processes telemetry data to provide real-time feedback.

Who it’s for

Virtual racers and sim racing teams who want to automate their pit crew operations, improve their driving skills through AI coaching, and manage complex race strategies without taking their hands off the wheel.

Highlights

  • AI Race Assistants: Includes a Race Engineer for pitstop automation, a Race Strategist for adapting to traffic and weather, a Race Spotter for safety warnings, and a Driving Coach for handling and skill improvement.
  • GPT Integration: Ability to connect assistants to LLMs to boost conversational expertise and allow for custom event/action definitions.
  • Setup & Strategy Workbenches: Tools for calculating fuel, developing race strategies, and analyzing telemetry to recommend car setup modifications.
  • Hardware Automation: Support for various external controllers and the ability to automate in-car settings (like ABS or traction control) based on track location.
  • Telemetry Analysis: An issue analyzer that automatically detects handling problems or driving style errors during a session.

Related

  • Project
    KINGSTON-115/llm-pid-tuner

    An LLM-assisted utility for PID tuning that analyzes system responses from hardware or simulations to automatically suggest and apply optimal control parameters.

  • Project
    microsoft/AirSim

    An open-source simulator for drones and cars built on Unreal Engine, designed as a platform for AI research in deep learning, computer vision, and reinforcement learning.

  • Project
    langwatch/scenario

    An agent testing framework that uses simulations, user simulators, and judge agents to evaluate the behavior and robustness of AI agents in multi-turn conversations.

  • Project
    suyiiyii/AutoGLM-GUI

    AutoGLM‑GUI is a desktop/Docker app that lets LLMs control Android phones via ADB. It offers chat‑based task execution, layered planning/execution agents, real‑time screen preview, multi‑device management, cron scheduling, workflow saving, conversation history, and an MCP API for integration with other AI tools.

  • Project
    CyberStrikeus/CyberStrike

    CyberStrike is an open‑source AI agent that turns any LLM (Claude, GPT, Gemini, etc.) into an autonomous penetration‑testing platform. It adds a security‑focused “intelligence layer”, ships 13+ specialised agents and 7,600+ signed security‑skill files, supports 150+ AI providers (including offline models), and can orchestrate real tools locally or on remote Bolt servers. A TUI, optional web UI, and built‑in HackBrowser complete the workflow.