π Funding π
If you find this project useful, please give it a star! Your support is appreciated and helps keep the project growing.π
Welcome to the Assistive AimGuide project!
This tool is designed to enhance accessibility for gamers with physical disabilities by providing advanced AI-driven aiming assistance. It helps to level the playing field, allowing everyone to enjoy competitive and casual gaming environments.
- π― Adaptive Aim Assistance: Tailors aiming assistance to the specific needs of gamers with physical disabilities, using YOLOv5 and YOLOv8 detection models.
- π« Precision Control: Allows for fine-tuning of aiming settings to ensure accessibility without overpowering gameplay.
- πΌοΈ Customizable Zones: Enables users to define areas on the screen for the tool to assist with, adapting to various game layouts and preferences.
- π» Dynamic Performance Adjustment: Manages resolution and processing based on system performance to maintain smooth gameplay.
- π€ Arduino Leonardo (optional): Integrates with Arduino for additional customization and hardware-based controls.
Join our Discord channel Assistive AimGuide for assistance, support, or to share your experience.
- Discord Link
- or Join to Support Fnbubbles420 Org & The Mission.
- Our community is growing be apart of something BIG!!
This tool is developed as an accessibility aid for gamers with disabilities to help them compete more effectively in games.
We advocate for fair play and accessibility in gaming and do not endorse cheating or the promotion of cheating in any form.
Use of this tool in online games is at your own risk. Please consult with game developers if unsure about compatibility with game policies.
This tool should be used primarily as an assistive device in environments that support inclusivity.
At FNBubbles420 Org, we are dedicated to supporting disabled gamers, developers, veterans, and streamers through various initiatives. One of our primary programs is Game Vision Aid, which aims to enhance accessibility and performance for gamers with visual impairments.
Game Vision Aid is coming soon β we are still testing and developing it to ensure it meets the highest standards for accessibility.
While the Assistive AimGuide is a separate project, it embodies our organization's dedication to leveraging innovative technologies to enhance accessibility and equality in gaming for those with disabilities. This commitment underlines our ongoing efforts to serve and uplift the community.
"Life is a journey best traveled together; when we lift each other up, we rise as a community, stronger and more united. Every small act of kindness creates ripples that can change the world."
β Bubbles
To learn more about what drives us, visit our Mission Page.
If you'd like to get involved or learn more about volunteering, visit our Volunteer Page.
Click the link to read Instructions π.
For AMD GPU SUPPORT click here
- Nvidia
- AMD
update_ultralytics.bat
ALWAYS CHECK FOR UPDATES COUPLE TIME EVERY FEW WEEKS !!
To run the bot, ensure the following dependencies are installed:
- Python 3.11.6 β The required Python version for compatibility.
- OpenCV β For handling image capture and processing (
pip install opencv-python
). - PyTorch β For deep learning and model inference (
pip install torch
). - Cupy β For utilizing CUDA-based GPU acceleration (
pip install cupy-cuda11x
). - BetterCam β For capturing and processing live game frames.
Enhanced Advanced
- Comtypes β For interacting with the Windows API (
pip install comtypes
).
The project has been successfully tested on the following setup:
- Processor: Intel(R) Core(TM) i7-14700F @ 2.10 GHz
- GPU: NVIDIA GeForce RTX 4060 Ti
- Operating System: Windows 11
- Python Version: 3.11.6
- Nvidia GPU
- AMD GPU
- CPU
- Multiple Monitor Support
.
βββ .github/ # GitHub configuration files
βββ Easy_Setup # Nvidia Easy Setup / Read, Follow Instructions in Terminal read the readme.md
βββ Environtmental_Setup # How The Environmental Variables The Correct Order
βββ Supported_Languages # Readme.md Supported Languages
βββ banner/ # Placeholder for banner or notice files
βββ main_amd_scripts/ # AMD_GPU - related script folder
β βββ dist/ # Distribution files for ONNX script
β βββ imgs/ # Contains images used in the project
β βββ models/ # Contains ONNX model files
β βββ pyarmor_runtime_000000/ # PyArmor runtime files for ONNX script (runtime for ONNX)
β βββ pyarmor_runtime_0000001/ # Additional PyArmor runtime files for ONNX script
β βββ ultralytics1/utils/ # Utility scripts from Ultralytics
β βββ utils/ # General utility scripts
β βββ amd_requirements.txt # Install Dependencies
β βββ butter-scotch-cookies.txt # Export Commands for models
β βββ config-launcher.bat # configuration launcher opens up in notepad
β βββ config.py # Configuration file for ONNX script
β βββ export.py # Python export script
β βββ gameSelection.py # Obfuscated game selection logic script
β βββ launcher.bat # Launcher for Main AMD
β βββ main_amd.py # Main AMD script
β βββ readme.md # Main Readme.md for AMD SUPPORT
β βββ readme2.md # Placing Pt Files
β βββ run-2.bat # Batch script to run the project FOR AMD GPUS
βββ main_cpu_script/ # CPU-related script folder
β βββ dist/ # Distribution files for CPU script
β βββ imgs/ # Contains images used in the project
β βββ models/ # Contains PyTorch model files
β βββ pyarmor_runtime_000000/ # PyArmor runtime files for CPU script
β βββ pyarmor_runtime_0000001/ # Additional PyArmor runtime files for CPU script
β βββ ultralytics1/utils/ # Utility scripts from Ultralytics
β βββ utils/ # General utility scripts
β βββ butter-scotch-cookies.txt # Export Commands for models
β βββ config-launcher.bat # configuration launcher opens up in notepad
β βββ config.py # Configuration file for CPU script
β βββ gameSelection.py # Obfuscated game selection logic script
β βββ launcher.bat # Launcher for Main CPU
β βββ main_cpu.py # Main CPU script
β βββ requirements.txt # Dependencies for CPU script
β βββ readme.md # Placing Pt Files
βββ main_onnx_script/ # ONNX-related script folder
β βββ dist/ # Distribution files for ONNX script
β βββ imgs/ # Contains images used in the project
β βββ models/ # Contains ONNX model files
β βββ pyarmor_runtime_000000/ # PyArmor runtime files for ONNX script (runtime for ONNX)
β βββ pyarmor_runtime_0000001/ # Additional PyArmor runtime files for ONNX script
β βββ ultralytics1/utils/ # Utility scripts from Ultralytics
β βββ utils/ # General utility scripts
β βββ butter-scotch-cookies.txt # Export Commands for models
β βββ config-launcher.bat # configuration launcher opens up in notepad
β βββ config.py # Configuration file for ONNX script
β βββ export.py # Python export script
β βββ gameSelection.py # Obfuscated game selection logic script
β βββ launcher.bat # Launcher for Main ONNX
β βββ main_onnx.py # Main ONNX script
β βββ readme.md # Placing Pt Files
βββ main_tensorrt_script/ # TensorRT-related script folder
β βββ dist/ # Distribution files for TensorRT script
β βββ imgs/ # Contains images used in the project
β βββ models/ # Contains TensorRT model files
β βββ pyarmor_runtime_000000/ # PyArmor runtime files for TensorRT script (runtime for TensorRT)
β βββ pyarmor_runtime_0000001/ # Additional PyArmor runtime files for TensorRT script
β βββ ultralytics1/utils/ # Utility scripts from Ultralytics
β βββ utils/ # General utility scripts
β βββ butter-scotch-cookies.txt # Export Commands for models
β βββ config-launcher.bat # configuration launcher opens up in notepad
β βββ config.py # Configuration file for TensorRT script
β βββ export.py # Python export script
β βββ gameSelection.py # Obfuscated game selection logic script
β βββ launcher.bat # Launcher for Main TensorRT
β βββ main_tensorrt.py # Main TensorRT script
β βββ readme.md # Placing Pt Files
βββ pt_models # PT MODELS
βββ ADDITION.MD # Addition.md Creator Developer Join Our Discord Support The Mission
βββ CODE_OF_CONDUCT.md # Code of conduct for the project
βββ LICENSE.MD # Project license file
βββ PLEASE-READ-IMPORTANT.md # VERY IMPORTANT MD _ PLEASE-READ-IMPORTANT.md
βββ SECURITY.md # Security policy for the project
βββ cudnn_instructions.js # Instructions related to cuDNN
βββ get_device.py # Lets you know if you installed CUDA
βββ gitattributes # Git attributes for handling line endings
βββ gitignore # Git ignore rules for excluding certain files
βββ install_python.bat # Batch script to install Python 3.11.6
βββ install_pytorch.bat # NEWEST VERSION OF PYTORCH (Nvidia)
βββ nodejs-instructions.ps1 # PowerShell script for Node.js instructions
βββ readme.md # Project README file
βββ nvidia_requirements.txt # Python dependencies for the project
βββ run.bat # Batch script to run the project
βββ update_ultralytics.bat # Batch script to update Ultralytics
- Ensure Node.js is installed on your system. You can download it from Node.js v22.12.0 (Windows 64-bit).
- During installation, if prompted, select "Add to PATH" by clicking Yes.
- Install Node.js Dependencies Navigate to the repository folder on your PC using the terminal and run:
npm install
- Run the Application Once the dependencies are installed, run the JavaScript file using:
node cudnn-instructions.js
- Expected Output The script will provide instructions for downloading and installing cuDNN and related components for your system.
- Make sure you are using
Node.js v20.17.0 or later
. - Ensure that
Node.js
was added to yoursystem's PATH
during installation.
-
Save the Script:
- Save the PowerShell script as
nodejs-instructions.ps1
in the desired directory.
- Save the PowerShell script as
-
Open PowerShell:
- Open PowerShell by searching for it in the Start Menu or pressing
Win + X
and selecting PowerShell.
- Set Execution Policy (If Needed):
- If this is your first time running a PowerShell script, you may need to allow script execution. Run this command:
Set-ExecutionPolicy RemoteSigned -Scope CurrentUser
- This will allow scripts that are locally created to run while ensuring scripts from external sources must be signed.
MAKE SURE TO TYPE YES OR Y IN THE FOR THE RESPONSE TO CONTINUE
- Navigate to the Script Directory:
- Use the
cd
command to navigate to the folder wherenodejs-instructions.ps1
is located. For example:
cd C:\Users\YourUsername\Desktop\Scripts
- Run the Script:
- To run the script, type the following command:
./nodejs-instructions.ps1
- Follow the Instructions:
- The script will guide you through the steps to install and verify Node.js, update npm, and run your JavaScript files.
- Mentioned selecting LTS for stability.
- Added a note about installing additional tools ( DO NOT INSTALL ANY ADDITIONAL TOOLS FROM NODE.JS )
- Included a step to update npm globally.
- Provided an example for the
cd
command to improve clarity. - Added instructions on how to install project dependencies using
npm install
. - Added clear instructions on how to run the
nodejs-instructions.ps1
PowerShell script, including enabling script execution.
- Install dependencies: Ensure you have Python and pip installed. Then run:
pip install -r nvidia_requirements.txt
Open the config.py
file and adjust the following settings according to your preferences:
- screenShotHeight and screenShotWidth: Define the portion of the screen to be captured around the center.
- useMask, maskSide, maskWidth, and maskHeight: Set these to mask parts of the screen where a model or object might interfere (useful in third-person games or for large weapons).
- aaMovementAmp: Controls how smooth the aim is. Adjust based on your preference and game type.
- aaQuitKey: Default is
8
, press this key to quit and shut down the auto-aim. - aaActivateKey =
CapsLock
, press to toggle the autoaim - confidence: Adjust detection confidence level for the target (default is
0.4
). - headshot_mode: Set to
True
to aim slightly upwards towards the head. - cpsDisplay: Set to
True
if you want to display corrections per second in the terminal (for debugging purposes). - visuals: Set to
True
to display what the bot "sees" (bounding boxes, etc.). - centerOfScreen: Prioritize targets near the center of the screen for smarter target selection.
- onnxChoice: Choose between
2
(AMD for nvidia), or3
(NVIDIA) when using ONNX models. - model_path: Uncomment the correct path based on whether you're using a TensorRT engine or ONNX model.
- Use
v5.engine
for TensorRT. - Use
v5.onnx
for ONNX.
- Use
- device: Set to
'cpu'
or'cuda'
depending on whether you're running on CPU or GPU. - fp16: Set to
True
to use FP16 for faster inference on supported GPUs.
After configuring the bot, navigate to the respective folder and start it by running:
- For the TensorRT bot, navigate to the
main_tensorrt_script/dist/
folder and run:
cd main_tensorrt_script/dist/
python main_tensorrt.py
- For the ONNX bot, navigate to the
main_onnx_script/dist/
folder and run:
cd main_onnx_script/dist/
python main_onnx.py
- Start/Stop: Use the Caps Lock key to toggle the bot on and off based on your game settings.
- Aim Adjustment: The bot automatically detects targets and prioritizes those near the center of the screen. It adjusts the aim smoothly. Adjust aim behavior through
aaMovementAmp
and other settings inconfig.py
. - Speed Values for Aim Adjustment:
- Slow: 0.2 - 0.4
- Medium: 0.5 - 0.7
- Fast: 0.8 - 1.0
- Very Fast: 1.1 - 1.5+
- Headshot Mode: Enable this mode to make the bot aim slightly upwards to target heads by setting
headshot_mode
to True.
- Exit: Press the '8' key to stop and exit the bot.
Modify settings in the config.py
file to customize bot behavior:
- Auto Aim Movement: Change the
aaMovementAmp
value to control how smoothly the bot adjusts aim. - Headshot Mode: Toggle headshot prioritization with
headshot_mode
. - Screen Resolution: Adjust the aim area using
screenShotWidth
andscreenShotHeight
. - Masking: Configure
useMask
,maskSide
,maskWidth
, andmaskHeight
to ignore certain screen areas. - Quit Key: Set
aaQuitKey
to customize the key used to quit the bot (default is 8). - Activation Key: Use Caps Lock to toggle the bot on/off.
- Confidence Level: Adjust the target detection confidence using the
confidence
setting. - Visual Feedback: Enable visual overlays with
visuals
to see what the bot detects. - Center Targeting: Use
centerOfScreen
to prioritize center-screen targets. - ONNX Provider: Choose between AMD or NVIDIA execution with
onnxChoice
. - Model Path: Specify the model file path in
model_path
, supporting.engine
or.onnx
. - Device: Set execution to 'cpu' or 'cuda' with
device
. - FP16 Mode: Enable
fp16
for faster processing on compatible GPUs.
- This tool is intended for educational and accessibility purposes within environments that support inclusivity.
- We do not endorse or promote cheating. Use of this tool in violation of game terms may result in bans or penalties.
- For any concerns about compatibility with game policies, consult game developers.
First, download the CUDA Toolkit 11.8 from the official NVIDIA website:
π Nvidia CUDA Toolkit 11.8 - DOWNLOAD HERE
- After downloading, open the installer (
.exe
) and follow the instructions provided by the installer. - Make sure to select the following components during installation:
- CUDA Toolkit
- CUDA Samples
- CUDA Documentation (optional)
- After the installation completes, open the
cmd.exe
terminal and run the following command to ensure that CUDA has been installed correctly:
nvcc --version
This will display the installed CUDA version.
Run the following command in your terminal to install Cupy:
pip install cupy-cuda11x
Download cuDNN (CUDA Deep Neural Network library) from the NVIDIA website:
π Download CUDNN. (Requires an NVIDIA account β it's free).
Open the .zip
cuDNN file and move all the folders/files to the location where the CUDA Toolkit is installed on your machine, typically:
C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8
Download TensorRT 8.6 GA.
Open the .zip
TensorRT file and move all the folders/files to the CUDA Toolkit folder, typically located at:
C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8
Once all the files are copied, run the following command to install TensorRT for Python:
pip install "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8\python\tensorrt-8.6.1-cp311-none-win_amd64.whl"
π¨ Note: If this step doesnβt work, double-check that the .whl
file matches your Python version (e.g., cp311
is for Python 3.11). Just locate the correct .whl
file in the python
folder and replace the path accordingly.
Add the following paths to your environment variables:
system path
C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8\lib
C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8\libnvvp
C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8\bin
Once you have CUDA 11.8 installed and cuDNN properly configured, you need to set up your environment via cmd.exe
to ensure that the system uses the correct version of CUDA (especially if multiple CUDA versions are installed).
You need to add the CUDA 11.8 binaries to the environment variables in the current cmd.exe
session.
Open cmd.exe
and run the following commands:
- DO each one
Separately
set PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8\bin;%PATH%
set PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8\libnvvp;%PATH%
set PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8\extras\CUPTI\lib64;%PATH%
These commands add the CUDA 11.8 binary, lib, and CUPTI paths to your system's current session. Adjust the paths as necessary depending on your installation directory.
- Verify the CUDA Version After setting the paths, you can verify that your system is using CUDA 11.8 by running:
nvcc --version
This should display the details of CUDA 11.8. If it shows a different version, check the paths and ensure the proper version is set.
-
Set the Environment Variables for a Persistent Session If you want to ensure CUDA 11.8 is used every time you open
cmd.exe
, you can add these paths to your system environment variables permanently: -
Open
Control Panel
->System
->Advanced System Settings
. Click onEnvironment Variables
. UnderSystem variables
, selectPath
and clickEdit
. Add the following entries at the top of the list:
C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8\bin
C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8\libnvvp
C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8\extras\CUPTI\lib64
This ensures that CUDA 11.8 is prioritized when running CUDA applications, even on systems with multiple CUDA versions.
- Set CUDA Environment Variables for cuDNN
If you're using cuDNN, ensure the
cudnn64_8.dll
is also in your system path:
set PATH=C:\tools\cuda\bin;%PATH%
This should properly set up CUDA 11.8 to be used for your projects via cmd.exe
.
- Ensure that your GPU drivers are up to date.
- You can check CUDA compatibility with other software (e.g., PyTorch or TensorFlow) by referring to their documentation for specific versions supported by CUDA 11.8.
import torch
print(torch.cuda.is_available()) # This will return True if CUDA is available
print(torch.version.cuda) # This will print the CUDA version being used
print(torch.cuda.get_device_name(0)) # This will print the name of the GPU, e.g., 'NVIDIA GeForce RTX GPU Model'
run the get_device.py
to see if you installed it correctly
The run.bat
script is a batch file to help you install all the required dependencies for this project. Below is the content of the file and the steps it will execute:
@echo off
echo Installing ONNX Runtime (GPU)...
pip install onnxruntime-gpu
echo Press enter to continue with the rest of the dependency installs
pause
echo Installing NumPy...
pip install numpy
echo Press enter to continue with the rest of the dependency installs
pause
echo Installing comtypes...
pip install comtypes
echo Press enter to continue with the rest of the dependency installs
pause
echo Installing OpenCV (opencv-python)...
pip install opencv-python
echo Press enter to continue with the rest of the dependency installs
pause
echo Installing pandas...
pip install pandas
echo Press enter to continue with the rest of the dependency installs
pause
echo Installing bettercam...
pip install bettercam
echo Press enter to continue with the rest of the dependency installs
pause
echo Installing onnx...
pip install onnx
echo Press enter to continue with the rest of the dependency installs
pause
echo Installing PyWin32...
pip install pywin32
echo Press enter to continue with the rest of the dependency installs
pause
echo Installing Dill...
pip install dill
echo Press enter to continue with the rest of the dependency installs
pause
echo Installing CuPy (GPU accelerated array library for CUDA 11.8)...
pip install cupy-cuda11x
echo Press enter to continue with the rest of the dependency installs
pause
echo Installing psutil...
pip install psutil
echo Press enter to continue with the rest of the dependency installs
pause
echo Installing colorama...
pip install colorama
echo Press enter to continue with the rest of the dependency installs
pause
echo Installing ultralytics...
pip install ultralytics
echo Press enter to continue with the rest of the dependency installs
pause
echo Installing PyAutoGUI...
pip install PyAutoGUI
echo Press enter to continue with the rest of the dependency installs
pause
echo Installing PyGetWindow...
pip install PyGetWindow
echo Press enter to continue with the rest of the dependency installs
pause
echo Installing pyyaml...
pip install pyyaml
echo Press enter to continue with the rest of the dependency installs
pause
echo Installing tqdm...
pip install tqdm
echo Press enter to continue with the rest of the dependency installs
pause
echo Installing matplotlib...
pip install matplotlib
echo Press enter to continue with the rest of the dependency installs
pause
echo Installing seaborn...
pip install seaborn
echo Press enter to continue with the rest of the dependency installs
pause
echo Installing requests...
pip install requests
echo Press enter to continue with the rest of the dependency installs
pause
echo Installing ipython...
pip install ipython
echo Press enter to continue with the rest of the dependency installs
pause
echo Installing dxcam...
pip install dxcam
echo Press enter to continue with the rest of the dependency installs
pause
echo Installing pyarmor...
pip install pyarmor
echo Press enter to continue with the rest of the dependency installs
pause
echo Installing serial...
pip install serial
echo Press enter to continue with the rest of the dependency installs
pause
echo Installing onnx-simplifier...
pip install onnx-simplifier
echo Press enter to continue with the rest of the dependency installs
pause
echo Installing onnxruntime...
pip install onnxruntime
echo Press enter to continue with the rest of the dependency installs
pause
echo MAKE SURE TO HAVE THE WHL DOWNLOADED BEFORE YOU CONTINUE!!!
pause
echo Click the link to download the WHL: press ctrl then left click with mouse
echo https://github.com/cupy/cupy/releases/download/v13.3.0/cupy_cuda11x-13.3.0-cp311-cp311-win_amd64.whl
pause
echo Installing CuPy from WHL...
pip install https://github.com/cupy/cupy/releases/download/v13.3.0/cupy_cuda11x-13.3.0-cp311-cp311-win_amd64.whl
pause
echo All packages installed successfully!
pause
-
Download the Required Files:
- Ensure you have downloaded the WHL file for CuPy from the following link: Download CuPy WHL
-
Run the Batch File:
-
Execute the
run.bat
file to automatically install all necessary Python dependencies for this project. -
The script will pause after each step so you can verify the installation. Simply press any key to continue after each pause.
To execute the batch file, you can use:
./run.bat
-
This guide will help you download and install Visual Studio 2022 Community Edition with the Desktop Development with C++ workload for C and C++ development.
Click the following link to download Visual Studio 2022 Community Edition:
π Download Visual Studio 2022 Community Edition
- Once the installer is downloaded, run the installer.
- In the Visual Studio Installer, select the Workloads tab.
To set up C++ development, ensure you select the Desktop development with C++ workload:
- In the Workloads tab, check the option Desktop development with C++.
- This will install the necessary tools for C++ programming, including compilers, libraries, and debugging tools.
- Click Install to begin the installation process.
Make sure your system meets the minimum requirements for Visual Studio 2022:
- OS: Windows 10 or higher.
- Processor: Quad-core processor or better.
- RAM: 8 GB of RAM (16 GB recommended).
- Disk Space: Minimum 20 GB free space.
If you encounter any issues during installation, refer to the official troubleshooting guide: