Jump to content
Frequently Asked Questions
  • Are you not able to open the client? Try following our getting started guide
  • Still not working? Try downloading and running JarFix
  • Help! My bot doesn't do anything! Enable fresh start in client settings and restart the client
  • How to purchase with PayPal/OSRS/Crypto gold? You can purchase vouchers from other users
  • Try asking for help in the chatbox
  • Python object detection botting


    Recommended Posts

    Hello everyone! 

    I was looking for a forum where I can discuss bot-related programming things with co-developpers. This is basically the most active forum where I stumbled upon, if there is a better forum for my questions, please let me know and I will move to that place! 🙂

    I was interested whether creating bots with object detection is still a thing. With the corona virus I have a lot of spare time so currently I am create bots which use object recognition to execute certain tasks. I am creating my own scripts in Python. I develop mouse movements and keystrokes with the 'pyautogui' library and I apply object-recognition with 'tensorflow'. Finally I create an overlay of the client with openCV.

    My curiosity to create these types of bots was drawn by articles such as:


    Or the Github repository of Luke Garbut who created a bot which is able to merch:


    Do you guys know where I can best post my questions regarding this type of botting and do you guys have any tips or remarkt on this type of botting? I would be very happy to find some sort of community where I can actively share my machine learning skills for object recognition. Any help is appreciated, thanks in advance!

    Link to comment
    Share on other sites

    This is certainly something you could do. Personally I made some pyautogui bots for RS3, but you can only automate easy tasks and those bots tend to break a lot. Hence I prefer using dreambot and writing an extensive anti-ban script.

    I did also use pyautogui on OSRS together with Runelite. Runelite lets you mark objects and then you just need to scan the screen for those marked bounding boxes, which is not really difficult. It's certainly a good project if you want to learn about neural networks, but for a decent bot I would not recommend using Python.

    Link to comment
    Share on other sites

    It can work but not sure if it's worth it. You will most likely be able to perform small tasks like fletching, cooking and things like that. Breaking is also a possibility with these type of bots but it depends. To be honest, you will have to test it yourself and see if it satisfies your needs.

    Link to comment
    Share on other sites

    My personal opinion: it's a fat waste of time. It's very much doable and if you have experience with OpenCV and tensorflow, have at it. It'll be a fun project. I tried learning OpenCV and tensorflow in c++ to create an object detection bot. It's not worth the time and it's a massive headache. The worst part is training the NN, and if something changes, have fun training it again. So, I came back here to make scripts in java, a language I hate with a passion. But hey, at least the dreambot API is 10/10 so I've had a good experience with java here.

    Link to comment
    Share on other sites

    • 1 year later...

    There are easier ways to escape the language. You can reflect in another runtime to work in whatever language you want. Implies a performance hit, but very flexible. It's how I've been prototyping using other languages.

    Link to comment
    Share on other sites

    Create an account or sign in to comment

    You need to be a member in order to leave a comment

    Create an account

    Sign up for a new account in our community. It's easy!

    Register a new account

    Sign in

    Already have an account? Sign in here.

    Sign In Now
    • Create New...

    Important Information

    We have placed cookies on your device to help make this website better. You can adjust your cookie settings, otherwise we'll assume you're okay to continue.