lizhang20

Efficient-Multimodal-LLMs-Survey

Efficient Multimodal Large Language Models: A Survey

remove-bg

Remove background directly in your browser, powered by WebGPU

13ft

My own custom 12ft.io replacement

whisperX

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

brutal

A neobrutalism Astro starter theme

squoosh

Make images smaller using best-in-class codecs, right in the browser.

L1B3RT45

JAILBREAK PROMPTS FOR ALL MAJOR AI MODELS

Qwen-Agent

Agent framework and applications built upon Qwen2, featuring Function Calling, Code Interpreter, RAG, and Chrome extension.

orbit

First framework to create radial interfaces using only CSS.

RMS-Runtime-Mobile-Security

Runtime Mobile Security (RMS) 📱🔥 - is a powerful web interface that helps you to manipulate Android and iOS Apps at Runtime

buster

Captcha solver extension for humans, available for Chrome, Edge and Firefox

nopecha-extension

Automated CAPTCHA solver for your browser. Works with Selenium, Puppeteer, Playwright, and more.

OpenVoice

Instant voice cloning by MIT and MyShell.

PasteBarApp

PasteBar - Limitless, Free Clipboard Manager for Mac and Windows

metube

Self-hosted YouTube downloader (web UI for youtube-dl / yt-dlp)

astro-theme-typography

Rediscover the beauty of typography.

Astro-Theme-Creek

A theme for Astro

Transcribro

Private and on-device speech recognition keyboard and service for Android.

astro-theme-mia

A minimalist, powerful astro theme with integrated rough-notation for engaging, informative content.

ripgrep-all

rga: ripgrep, but also search in PDFs, E-Books, Office documents, zip, tar.gz, etc.

rudroid

Rudroid - Writing the World's worst Android Emulator in Rust 🦀

OpenAdapt

AI-First Process Automation with Large ([Language (LLMs) / Action (LAMs) / Multimodal (LMMs)] / Visual Language (VLMs)) Models

screen_qa

ScreenQA dataset was introduced in the "ScreenQA: Large-Scale Question-Answer Pairs over Mobile App Screenshots" paper. It contains ~86K question-answer pairs collected by human annotators for ~35K screenshots from Rico. It should be used to train and evaluate models capable of screen content understanding via question answering.

ActivityLauncher

Activity launcher creates shortcuts for any installed app and hidden activities to launch them with ease

lossless-cut

The swiss army knife of lossless video/audio editing

Android-Emulator-image

The use of this Docker image simplifies the process of running an Android emulator within a Docker container

MiniCPM-V

MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone

ml-ferret

ShortcutsBench

ShortcutsBench: A Large-Scale Real-World Benchmark for API-Based Agents

Agent-Eval-Refine

Code for Paper: Autonomous Evaluation and Refinement of Digital Agents