> [!CAUTION] > # This tool is No Longer Supported by RootKit > We will not offer help for issues that arise with this program, or assist in getting it running on your machine. > You are free to fork and edit this tool yourself. # ๐ŸŽฏ World's Best AI Aimbot ๐ŸŽฎ ![World's Best AI Aimbot Banner](imgs/banner.png) [![Pull Requests Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat)](https://makeapullrequest.com) Want to make your own bot? Then use the [Starter Code Pack](https://github.com/RootKit-Org/AI-Aimbot-Starter-Code)! -- -- ## ๐Ÿ™Œ Welcome Aboard! We're a charity on a mission to educate and certify the upcoming wave of developers in the world of Computer Engineering ๐ŸŒ. ~~Need assistance? Hop into our [Discord](https://discord.gg/rootkitorg) and toss your questions at `@Wonder` in the *#ai-aimbot channel* (be sure to stick to this channel or face the consequences! ๐Ÿ˜ฌ). Type away your query and include `@Wonder` in there.~~ Our *AI Aimbot* ๐Ÿค– sharpshoots targets in **any game with humanoid characters**, harnessing the power of [YOLOv5](https://github.com/ultralytics). Currently, it's a ninja against anti-cheat systems, as it's visual-only. Still, watch out for manual player reports! ๐Ÿ‘€ Intended for educational use ๐ŸŽ“, our aim is to highlight the vulnerability of game devs to AI-driven cheats. Pass it along to your game developer buddies, and save their games from being outsmarted! **โš  Use at your own risk! If you're caught... well, you've been warned!** ## ๐Ÿ“น Instructional Media - [Watch the tutorial video (Works But Outdated)](https://www.youtube.com/watch?v=TCJHLbbeLhg) - [Watch the live stream explainer (Works But Outdated)](https://www.youtube.com/watch?v=uniL5yR7y0M&ab_channel=RootKit) - [Join the Discord](https://discord.gg/rootkitorg) ## There are 3 Versions ๐Ÿš€๐Ÿšฆ๐Ÿ–ฅ๏ธ - Fast ๐Ÿƒโ€โ™‚๏ธ - `main.py` โœ… Easy to set up, Works on any computer ๐Ÿ’ป - Faster ๐Ÿƒโ€โ™‚๏ธ๐Ÿ’จ - `main_onnx.py` โš™๏ธ May need to edit a file, Works on any computer ๐Ÿ’ป - Fastest ๐Ÿš€ - `main_tensorrt.py` ๐Ÿข Enterprise level hard, Works on computers with Nvidia GPUs only ๐ŸŽฎ ## ๐Ÿงฐ Requirements - Nvidia RTX 980 ๐Ÿ†™, higher or equivalent - And one of the following: - Nvidia CUDA Toolkit 11.8 [DOWNLOAD HERE](https://developer.nvidia.com/cuda-11-8-0-download-archive) ## ๐Ÿš€ Pre-setup Steps 1. Download and Unzip the AI Aimbot and stash the folder somewhere handy ๐Ÿ—‚๏ธ. 2. Ensure you've got Python installed (like a pet python ๐Ÿ) โ€“ grab version 3.11 [HERE](https://www.python.org/downloads/release/python-3116/). - ๐Ÿ›‘ Facing a `python is not recognized...` error? [WATCH THIS!](https://youtu.be/E2HvWhhAW0g) - ๐Ÿ›‘ Is it a `pip is not recognized...` error? [WATCH THIS!](https://youtu.be/zWYvRS7DtOg) 3. Fire up `PowerShell` or `Command Prompt` on Windows ๐Ÿ”. 4. To install `PyTorch`, select the appropriate command based on your GPU. - Nvidia `pip install torch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2 --index-url https://download.pytorch.org/whl/cu118` - AMD or CPU `pip install torch torchvision torchaudio` 5. ๐Ÿ“ฆ Run the command below to install the required Open Source packages: ``` pip install -r requirements.txt ``` ## ๐Ÿ”Œ How to Run (Fast ๐Ÿƒโ€โ™‚๏ธ Version) Follow these steps **after** Python and all packages have been installed: 1. Open `PowerShell` โšก or `Command Prompt` ๐Ÿ’ป. 2. Input `cd `, then drag & drop the folder containing the bot code into the terminal. 3. Hit Enter โ†ฉ๏ธ. 4. Type `python main.py` and press Enter. 5. Use **CAPS_LOCK** to toggle the aimbot ๐ŸŽฏ. It begins in the *off* state. 6. Pressing `q` ๐Ÿ’ฃ at **ANY TIME** will shut down the program. ## ๐Ÿ”Œ How to Run (Faster ๐Ÿƒโ€โ™‚๏ธ๐Ÿ’จ Version) Follow these steps **after** Python and all packages have been installed: 1. Open the `config.py` ๐Ÿ“„ file and tweak the `onnxChoice` variable to correspond with your hardware specs: - `onnxChoice = 1` # CPU ONLY ๐Ÿ–ฅ - `onnxChoice = 2` # AMD/NVIDIA ONLY ๐ŸŽฎ - `onnxChoice = 3` # NVIDIA ONLY ๐ŸŽ๏ธ 2. IF you have an NVIDIA set up, run the following ``` pip install onnxruntime-gpu pip install cupy-cuda11x ``` 2. Follow the same steps as for the Fast ๐Ÿƒโ€โ™‚๏ธ Version above except for step 4, you will run `python main_onnx.py` instead. ## ๐Ÿ”Œ How to Run (Fastest ๐Ÿš€ Version) Follow these sparkly steps to get your TensorRT ready for action! ๐Ÿ› ๏ธโœจ 1. **Introduction** ๐ŸŽฌ Watch the TensorRT section of the setup [video ๐ŸŽฅ](https://www.youtube.com/watch?v=uniL5yR7y0M&ab_channel=RootKit) before you begin. It's loaded with useful tips! 2. **Oops! Don't Forget the Environment** ๐ŸŒฑ We forgot to mention adding environmental variable paths in the video. Make sure to do this part! 3. **Get Support If You're Stumped** ๐Ÿค” If you ever feel lost, you can always `@Wonder` your questions in our [Discord ๐Ÿ’ฌ](https://discord.gg/rootkitorg). Wonder is here to help! 4. **Install Cupy** Run the following `pip install cupy-cuda11x` 5. **CUDNN Installation** ๐Ÿงฉ Click to install [CUDNN ๐Ÿ“ฅ](https://developer.nvidia.com/downloads/compute/cudnn/secure/8.9.6/local_installers/11.x/cudnn-windows-x86_64-8.9.6.50_cuda11-archive.zip/). You'll need a Nvidia account to proceed. Don't worry it's free. 6. **Unzip and Relocate** ๐Ÿ“โžก๏ธ Open the .zip CuDNN file and move all the folders/files to where the CUDA Toolkit is on your machine, usually at `C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8`. 7. **Get TensorRT 8.6 GA** ๐Ÿ”ฝ Fetch [`TensorRT 8.6 GA ๐Ÿ›’`](https://developer.nvidia.com/downloads/compute/machine-learning/tensorrt/secure/8.6.1/zip/TensorRT-8.6.1.6.Windows10.x86_64.cuda-11.8.zip). 8. **Unzip and Relocate** ๐Ÿ“โžก๏ธ Open the .zip TensorRT file and move all the folders/files to where the CUDA Toolkit is on your machine, usually at `C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8`. 9. **Python TensorRT Installation** ๐ŸŽก Once you have all the files copied over, you should have a folder at `C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8\python`. If you do, good, then run the following command to install TensorRT in python. ``` pip install "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8\python\tensorrt-8.6.1-cp311-none-win_amd64.whl" ``` ๐Ÿšจ If the following steps didn't work, don't stress out! ๐Ÿ˜… The labeling of the files corresponds with the Python version you have installed on your machine. We're not looking for the 'lean' or 'dispatch' versions. ๐Ÿ” Just locate the correct file and replace the path with your new one. ๐Ÿ”„ You've got this! ๐Ÿ’ช 10. **Set Your Environmental Variables** ๐ŸŒŽ Add these paths to your environment: - `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` 11. **Download Pre-trained Models** ๐Ÿค– You can use one of the .engine models we supply. But if it doesn't work, then you will need to re-export it. Grab the `.pt` file here for the model you want. We recommend `yolov5s.py` or `yolov5m.py` [HERE ๐Ÿ”—](https://github.com/ultralytics/yolov5/releases/tag/v7.0). 12. **Run the Export Script** ๐Ÿƒโ€โ™‚๏ธ๐Ÿ’ป Time to execute `export.py` with the following command. Patience is key; it might look frozen, but it's just concentrating hard! Can take up to 20 minutes. ``` python .\export.py --weights ./yolov5s.pt --include engine --half --imgsz 320 320 --device 0 ``` Note: You can pick a different YOLOv5 model size. TensorRT's power allows for larger models if desired! If you've followed these steps, you should be all set with TensorRT! โš™๏ธ๐Ÿš€ ## โš™๏ธ Configurable Settings *Default settings are generally great for most scenarios. Check out the comments in the code for more insights. ๐Ÿ” The configuration settings are now located in the `config.py` file!
**CAPS_LOCK is the default for flipping the switch on the autoaim superpower! โš™๏ธ ๐ŸŽฏ** `useMask` - Set to `True` or `False` to turn on and off ๐ŸŽญ `maskWidth` - The width of the mask to use. Only used when `useMask` is `True` ๐Ÿ“ `maskHeight` - The height of the mask to use. Only used when `useMask` is `True` ๐Ÿ“ `aaQuitKey` - The go-to key is `q`, but if it clashes with your game style, swap it out! โŒจ๏ธโ™ป๏ธ `headshot_mode` - Set to `False` if you're aiming to keep things less head-on and more centered. ๐ŸŽฏโžก๏ธ๐Ÿ‘• `cpsDisplay` - Toggle off with `False` if you prefer not to display the CPS in your command station. ๐Ÿ’ป๐Ÿšซ `visuals` - Flip to `True` to witness the AI's vision! Great for sleuthing out any hiccups. ๐Ÿ•ต๏ธโ€โ™‚๏ธโœ… `aaMovementAmp` - The preset should be on point for 99% of players. Lower the digits for smoother targeting. Recommended doses: `0.5` - `2`. โš–๏ธ๐Ÿ•น๏ธ `confidence` - Stick with the script here unless you're the expert. ๐Ÿงโœจ `screenShotHeight` - Same as above, no need for changes unless you've got a specific vision. ๐Ÿ“๐Ÿ–ผ๏ธ `screenShotWidth` - Keep it constant as is, unless you've got reasons to adjust. ๐Ÿ“๐Ÿ–ผ๏ธ `aaDetectionBox` - Default's your best bet, change only if you've got the know-how. ๐Ÿ“ฆโœ… `onnxChoice` - Gear up for the right graphics cardโ€”Nvidia, AMD, or CPU power! ๐Ÿ’ป๐Ÿ‘พ `centerOfScreen` - Keep this switched on to stay in the game's heart. โค๏ธ๐Ÿ–ฅ๏ธ ## ๐Ÿ“Š Current Stats The bot's efficiency depends on your setup. We achieved 100-150 CPS with our test specs below ๐Ÿš€. - AMD Ryzen 7 2700 - 64 GB DDR4 - Nvidia RTX 3080 ๐Ÿ’ก Tip: Machine Learning can be tricky, so reboot if you keep hitting CUDA walls. ## ๐Ÿค Community Based We're all about collaboration. Your contributions can earn you credit and potential ๐Ÿ’ฐ! **Want to volunteer? Have video or program ideas? Tell us!** ## โš ๏ธ Known Cheat-Detectable Games Splitgate (reported by a Discord user ๐Ÿ•ต๏ธโ€โ™‚๏ธ), EQU8 detects win32 mouse movement library. ## ๐Ÿš€ Custom Aimbots and Models Show off your work or new models via Pull Requests in `customScripts` or `customModels` directories, respectively. Check out the `example-user` folder for guidance. ## ๐ŸŒ  Future Ideas - [x] Mask Player to avoid false positives Happy Coding and Aiming! ๐ŸŽ‰๐Ÿ‘พ