SunOner/sunone_aimbot_2

Aim-bot based on AI for all FPS and TPS games

Sunone Aimbot 2 is a Windows program (written in C++17) that uses an AI model to detect targets on your screen and automatically aims your mouse at them. You provide the AI model (a .onnx file), and the program runs it locally on your computer.

Two ready-to-use versions — you don't need to compile anything:

  • CUDA + TensorRT build — for NVIDIA GPUs (GTX 1660, RTX 2000/3000/4000/5000). Requires the latest NVIDIA driver and CUDA 13.1 installed. Not supported on older GTX 10xx/Pascal cards.
  • DirectML (DML) build — works on any modern GPU (NVIDIA, AMD, Intel, even integrated graphics). No extra software needed. Recommended for older NVIDIA cards, AMD Radeon, Intel Iris/Xe, and laptops.

How to use it:

  1. Download and unpack your chosen version (prebuilt .exe files are shared on the project's Discord server).
  2. Run ai.exe. The first launch exports the model, which can take up to 5 minutes.
  3. Put your .onnx model in the models folder and select it in the overlay (press HOME to open/close the overlay).
  4. All settings are in the overlay.

Controls:

  • Right Mouse Button — aim at the detected target
  • F2 — exit
  • F3 — pause aiming
  • F4 — reload config
  • HOME — open/close overlay

Building from source is possible for advanced users, with instructions in docs/build.md. The project also includes documentation for the config.ini file and a setup/FAQ/troubleshooting guide.

Under the hood: it uses TensorRT, OpenCV, ImGui, CppWinRT, and GLFW (among others). OpenCV is licensed under Apache 2.0, ImGui under MIT.

Community & support: The project is developed with help from supporters on Boosty and Patreon, who get access to better-trained AI models. Help and contributions happen on the Discord server or via GitHub issues.

Related

  • Project
    Babyhamsta/Aimmy

    An AI-based aim alignment tool that uses YOLOv8 and DirectML to help gamers with physical or visual impairments improve their accuracy in FPS games.

  • Project
    xlite-dev/lite.ai.toolkit

    A lightweight C++ toolkit providing a unified API to deploy over 300 AI models using backends like ONNXRuntime, MNN, and TensorRT.

  • Project
    AimRT/AimRT

    AimRT is a lightweight C++ runtime framework for modern robotics that integrates robot end-side, edge, and cloud deployments for AI-powered applications.

  • Project
    NVIDIA/TensorRT-Edge-LLM

    TensorRT Edge-LLM is a high-performance C++ inference runtime that enables developers to run large language and vision models on NVIDIA edge hardware like Jetson and DRIVE for robotics and automotive applications.

  • Project
    cyrusbehr/YOLOv8-TensorRT-CPP

    A C++ implementation of YOLOv8 using TensorRT for high-performance GPU inference, supporting object detection, semantic segmentation, and pose estimation.