Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Back to feed
orasul 
posted an update 2 days ago
Post
254
hi, it is deki and now I am multithreaded - Android AI agents based on Object detection and LLM

I added a support for running several AI agents at the same time to my project - deki.

It is a model that understands what’s on your screen and can perform tasks based on your voice or text commands.

Some examples:
* "Write my friend "some_name" in WhatsApp that I'll be 15 minutes late"
* "Open Twitter in the browser and write a post about something"
* "Read my latest notifications"
* "Write a linkedin post about something"

Android, ML and Backend codes are fully open-sourced.
I hope you will find it interesting.

Github: https://github.com/RasulOs/deki

License: GPLv3
sulaman786
•
edited about 16 hours ago

Love the project! If you ever want to make your agent prompt logic or fallback flows more scalable, you might want to check out CodeLibrary.ai (https://www.codelibrary.ai) .we use it to organize agent reasoning patterns with MCP-style structure.
image 123.png

orasul

By the way, just deployed the model on spaces:

https://huggingface.co/spaces/orasul/deki

You can check Analyze & and get YOLO and then action endpoint to see the capabilities of the model

ProCreations

Is there an APK to install this or is it on google play?

·
orasul
•
edited 2 days ago

For now users should build android package and run server themselves (because it is more like a research, proof of concept) but in the future I will make it fully local (OCR, Object detection, Image processing, LLM) and will upload the build to the play store and on other platforms

In this post