@THEbluefirestudios

These are the features i have decided:

Repair & Cleanup

Fix my PC ⟵ done
Reinstall Windows ⟵ use systemreset.exe or shutdown /r /o into WinRE
Clear Cache & Temp Files
Clean Registry Keys ⟵ scour Win11Debloat GitHub for safe list + reg files !!
Memory Manager !! ⟵ use psutil
Deep Uninstall !!

Performance & Optimization

Update Drivers & Apps ⟵ winget upgrade –all
Startup Time Booster ⟵ winreg on Run keys + schtasks
Gaming Mode !! ⟵ psutil process list matched against hardcoded game names, psutil.Process.nice()
Refresh Display Drivers ⟵ done
Stress Test (WinSat) ⟵ winsat subprocess call
WiFi Reset ⟵ done

Windows Customization

Windows Debloat !! ⟵ Win11Debloat GitHub, ship their .reg files as toggles with undo pairs
Remove All Windows AI Features ⟵ Win11Debloat GitHub, same .reg toggle approach
Actually Autosave (Office) !! ⟵ interval mode: pyautogui.hotkey(‘ctrl’,‘s’) on timer, aggressive mode: watch ~$ temp file mtime with os.path.getmtime
Find Similar Files !! ⟵ difflib.SequenceMatcher on filenames, group by similarity score

File Management

Downloads & Desktop Organizer !! ⟵ os/shutil + extension-to-folder mapping
Bulk File Rename ⟵ regex pattern based os.rename loop
Local File Converter ⟵ FFmpeg subprocess wrapper
FFmpeg GUI ⟵ dropdown UI → FFmpeg subprocess
HyprImage ⟵ Pillow wrapper with action picker

Productivity Tools

Voice Typing ⟵ speech_recognition + pyautogui to paste output
OCR: Image to Text ⟵ pytesseract or easyocr
Pretend to Type ⟵ pyautogui.typewrite() with interval, probably fold into Macro Creator
Macro Creator ⟵ record: keyboard lib + pyautogui polling, playback: screen color check before each click
HyprSearch !! ⟵ global hotkey via keyboard lib, fuzzy file search via os.walk + difflib
Terminal Command Generator ⟵ dropdown UI → command string builder
Colorpicker ⟵ pyautogui.pixel() grab + magnifier overlay

Extras & Fun

Hyprclicker ⟵ done (existing autoclicker)
Mouse Wraparound ⟵ done
Image to ASCII ⟵ same approach as Bad Apple project
Camera to ASCII (Virtual Cam) ⟵ OpenCV capture → ASCII render → OBS virtual cam, hardest feature overall
Desktop Pet !! ⟵ transparent tkinter window + sprite animation, WS_EX_LAYERED for click-through
Fake Update Screen ⟵ fullscreen tkinter canvas + fake progress bar
Fake Error Screen ⟵ same, BSOD-style overlay

(raw list organised by Anything AI)

I have finished the simpler features

Ok i have added the features: mouse wraparound, open Chris Titus Tools, Fix PC button and Reset WIFI button, will add more

Wow, this 3D -printerless Hackpad is becoming very messy.

Before you call me stupid, the customs on PCBs and 3D printed parts here in India is ENORMOUS, and I am brokie brokie.

Mybe I’ll make a proper hackpad soon.

Damn man…. so much for adding chat history and long term memory….

Today I spent 1 and a half hours adding them, the memory is stored in Anything AI\memory and chats are stored in Anything AI\chats. I also switched the sorter AI to deepseek-ai/DeepSeek-R1-Distill-Llama-70B coz llama was hallucinating a LOT, ill be releasing another beta soon…..

I’m regretting making a TUI instead of a GUI.

I made it so because i wanted to save time and focus on the important stuff, and cause i was lazy, but it turned out to be a mistake.

Today I spent nearly an hour trying to fix terminal formatting issues like shown in the attached screenshot (sorry for low resolution) , it got so bad that I just ended making my own input() function instead. Truly an experience, anyways, Anything has entered beta! The full proper official ship will come soon!

Now I have created the logo for Anything AI, so it will be definitely out soon! I hope this project gets high ratings!

Lapse:
https://lapse.hackclub.com/timelapse/kOucepr-Hpub

YESS, attach file works! It currently supports .txt, .csv, .docx, .pptx, .xlsx and code files like .py, .kt, .java, .cpp and, obviously image files, the ones supported by PIL :). Anything AI will be finished soon!

Today I’m working on adding more modalities to my AI, more specifically, giving it the ability to read text, documents and code files alongside the already implemented image file. To do this I’m migrating from pick_image_file() to just pick_file()

As of now, the pick_file() function is done and i need to add functions for parsing the returned filepath to data the AI can read.

I also ran out of free credits on Hugging Face so i created an extra account. :(

OK, so terminal commands work! I also fixed the jank bug that caused issues with displaying text after addingf an image to a prompt. Things seem to be going well! I’m gonna make myself a bowl of maggi now >. <

Ok so, I know this is a project I started before Stardance on May 25 2026 and have worked for hours on this, and its almost ship ready, I’ve added everything I want like multimodal input, file generation, etc.

As of now, I’m giving it the ability to run terminal commands and do some bugfixing before shipping it as an .exe