MyRobot (January Update)
A downloadable game
We recently achieved full funding on our Kickstarter! Many features are coming:
PLEASE DO NOT DONATE. Instead consider a PATREON membership because then I can give you AI access.
This is an Adventure Character Simulator with optional AI features featuring your own robot that you can build and explore with.
January Build is now available for free here at itch.io!
This is my next big character companion game featuring a customizable robot with ChatGPT and AI based awareness. You can cutomize clothing with AI text to image and explore an in-development growing map!
Download
Click download now to get access to the following files:
Development log
- MyRobot Development Blog 12/24/24 - Better Robot Stats!17 days ago
- FINAL KICKSTARTER HOURS19 days ago
- MyRobot Development Blog 12/7/24 Robot Upgrades!22 days ago
- JANUARY BUILD NOW FREE!28 days ago
- KICKSTARTER UPDATE!28 days ago
- MyRobot Development Blog 11/16/2431 days ago
- VR Milestone ALMOST!34 days ago
- MyRobot DevBlog 11/9/24 - Planning!38 days ago
Comments
Log in with itch.io to leave a comment.
when is it coming for mac?
[Context Shifting: Erased 7 tokens at position 2]
Processing Prompt (10 / 10 tokens)
Generating (77 / 512 tokens)
(EOS token triggered! ID:128009)
[10:06:31] CtxLimit:3661/4096, Amt:77/512, Init:0.05s, Process:1.29s (129.4ms/T = 7.73T/s), Generate:14.34s (186.2ms/T = 5.37T/s), Total:15.63s (4.93T/s)
Output: <Generated Message>
Generate: The response could not be sent, maybe connection was terminated?
the connection getting terminated. i run local LLM with kobaldcpp as per the documentation of this game.
can you able to analyze what's going on here?
If it took you 14 seconds to generate a response perhaps your computer isnt powerful enough to generate offline? What are your computer specs?
I don't have GPU. I run Llama 3B parameter model. it runs in CPU only hence response is slower . 12 core CPU.
I use Wine compatible layer to run your game in Linux.
Thanks for replying and trying to help. I like your game testing it. i will buy it soon
Hi sgthale! Apparently, the game isn't labeled as compatible on itch.io, preventing installations. please fix I rlly wanna play!
You can manually download it and install it just now with the itchio client.
Help! what should I do if I run this application and it returns error 0x00000050?(I'm on windows 7)
i dont know if it supports windows 7? Maybe you need a better graphics card with DX12
Will being able to run through an LLM be an option?
of course you can already do that!
Oh, wow, thats cool!
I was very skeptical at first, but after looking at the Kickstarter and Discord, this can easily be the VIVA successor we needed. Thank you for the hard work and I wish you much luck.
thanks
Please add Russian language support. A very large audience needs it
okay!
What would be interesting if there was an android/windows/linux/mac versions with apis already included so inexperienced people could explore this game in its entirety. looks great btw.
pleaseeeee add modding support
Mod support is on the Kickstarter goal list above. So, yes, there will be Steam Workshop mod support.
How do you play it? I am on a fire tablet and it only goes to my Amazon files
little bro get of itch and go play with playdough
Can I use Gemini AI's api key?
I get an issue using Kobold_CPP, where I talk, it sends, and it generates fine, but the game connection seems to terminate after generation.
im also with the same struggle, lemme know if you get any responses plss
That's what It's doing here, though terminating before generation, saying it can't connect, even though it is.
Sounds like you are using too strong of an AI file for your hardware or settings aren't set quite right. I had the same issue but It took me some fiddling on settings before I got it to work. When Kobold_cpp first starts, it is looking at your CPU. Mine is not great so I had to switch it to use my GPU more through I think it was Vulkan Old CPU.
I think it would be great if they released a free beta on Steam. 👀
yeah we are not at that stage yet
this is very promising and i myself have been testing and messing with connecting LLM's to a game world. I am wondering about though, when using local LLM does the game tell the LLM about the robots stats, body and what it can perform in terms of actions? i read that currently there is a limitation with function calling but would love to hear more about how this works :)
do you parse the actions from the text generated, or perhaps make the llm generate both speech and actions seperately or something like that?
yeah I inject messages to the chat for the game.
yes I parse actions manually sometimes depending on the action.
So i kind of took a look at the code and if i am not mistaken, are you not sending the tool list when using a local llm?
are you sending the tools as
messages=[{"role": "user", "content": "What is the weather like in Paris today?"}], tools=toolsor is the tools like this?
messages=[{"role": "user", "content": "What is the weather like in Paris today?", "role": "tools", "content":"{{tool_list}}"}]neither, loop up tool calls on OpenAI API docs
what a fascinating project, I'm eager to try it!
will there be a linux build?
You can likely run the game with wine, or using steams compatibility softwares
works, it's how I've been running it.
Is there a way to use openai api keys?
make us able to throw hands
AND PLEASE add mac support
Fascinating.
very hopeful for a macos build or native linux build in the future. <3 keep up the good work.
Beautiful game.
I like how you added the option for self hosted ai. Could you also add a primitive TTS solution for self hosted tts?
yea
why i can't donate you?
Wth is this ?
the blue rocks are not glowing. im trying to farm
them for money but they are not high lighting. help!
how to pick up iridium, there are stones with blue pieces but I can't pick anything,
Use scan to find small pieces of iridium (on the ground).
Well, I just went through all the places, and I didn't find anything.
i tried talking to the robot, but it said "No Audio Stream". what to do after this?
The robot only follows me and answer random things. like she doesn't understand anything and the prompt only works with the default prompt
That's because the default prompt gives her the intelligence of a 4 year old. So I fiddled with the prompt quite a bit to make them more useful. I upped the age of intelligence first and then just gave them an overwhelming yandere obsession with the player in the prompt and removed the word short from the original prompt. Much more talkative and helpful to be honest. I'm using a local LLM though so not sure if you are as well.
What LLM model would you suggest? I tried some i had laying around but they didn't seem to play nice with the game.
I just noticed the "Help" button in game, gonna try that model out.
How to make her speak?
is it still not possible?
what no it is! You can use local hosting to make her speak for free or use the online paid service.
They might mean as in having a voice.
A workaround would be to set up Kobold to do the voice if you are hosting locally.
well, i have a issue with my gameplay (i play the December build, also free member) the issue is mostly about the Shop and some other things like the problem of after reloading the game, the pc in game doesn't work (if other asking, i'm from Spain, Europe, so yeah, i will wait till the public release of the january build)
Ok! I fixed those issues. It's out now!
what does iridium look like?
it has a blueish look, so mostly the scanners will be useful
how do you install the ai
for now the only option is wait the release of the public release of the january version, also we can't make the robot talk so we would need a tts program with a custom AI token that we maked, so yeah we would need the public release of the january build
where's the last piece of iridium? 🫠
I have fixed local hosting: CREAsTIVE/MyRobotLocalServerFix: Local Server fix for MyRobot game
is this for the december version?
Yes
not working
You can create issue with your'e problem on my github and i will help you
and 2025
Mmh very cool however we moved away from oobabooga to OpenAI front ends. This is coming out for the public for free in 11 days!
Failed to connect to LLM
Its better to create a single interface IChatCompletioner (instead of youre ChatManager) stored in a Game class, and do 3 (or even more) implementations of that interface for patreon, ChatGPT API and Oobabooga IMO. + It would be easier to fix that issue with mods
Is it possible to use my API key for text generation?
Чи є локальний AI-хостинг з oobabooga безкоштовним?
How do you setup a LLM locally? Where can we download it? Is it possible to provide it with the game?
If i may ask will you put this on steam if you do I'll buy it their pls put it on steam I really like the game