The plan: enhance LLM cooperation by leveraging Windows UI Automation.
Video demo
If you have a DualShock controller, you will need something like DS4Windows.
- TeamDman/voice2text: A python program that types what you say if you're holding the hotkey (github.com)
- ollama/ollama: Get up and running with Llama 2, Mistral, and other large language models. (github.com)
- PTA-Text: A Text Only Click Model - Prompt image, it tells you where it would click (demo)
- Set-of-Mark Visual Prompting for GPT-4V
- LLaVA
- YOLOv9
-
OpenAdaptAI/OpenAdapt: AI-First Process Automation with Large Multimodal Models (LMMs)
-
TobiasNorlund/UI-Act: An AI agent for interacting with a computer using the graphical user interface
-
KillianLucas/open-interpreter: A natural language interface for computers
-
Accessibility tools - AccEvent (Accessible Event Watcher) - Win32 apps | Microsoft Learn
-
Accessibility tools - Inspect - Win32 apps | Microsoft Learn
-
Navigation events for WebView2 apps - Microsoft Edge Developer documentation | Microsoft Learn
-
(1) Building 25+ years of SysInternals: Exploring ZoomIt | BRK200H - YouTube
-
c# - Getting icon of "modern" Windows app from a desktop application? - Stack Overflow
- stillonearth/bevy_rl
- Saving RenderTarget image data to a file #5603
- paulkre/bevy_image_export: Bevy plugin for rendering image sequences
- guidance-ai/guidance: A guidance language for controlling large language models.
- Eladlev/AutoPrompt: A framework for prompt tuning using Intent-based Prompt Calibration (github.com)
- openai/whisper-large-v2: Hugging Face
- m-bain/whisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
- SYSTRAN/faster-whisper: Faster Whisper transcription with CTranslate2
- collabora/WhisperLive: A nearly-live implementation of OpenAI's Whisper
- gaborvecsei/whisper-live-transcription: Live-Transcription (STT) with Whisper PoC (github.com)
- FL33TW00D/whisper-turbo: Cross-Platform, GPU Accelerated Whisper 🏎️ (github.com)
- beartype
- facebookresearch/torchdim: Named tensors with first-class dimensions for PyTorch
- Are we learning yet? A work-in-progress to catalog the state of machine learning in Rust
- PyO3/pyo3: Rust bindings for the Python interpreter