TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

Running Docling as an API service

Mac app that shows all open files, directories, sockets, pipes and devices in use by all running processes. Nice GUI for lsof.

Fast Diversification for Search & Retrieval

The best ChatGPT that $100 can buy.

Like Vercel, but open source and for all languages.

💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows

In-depth tutorials on LLMs, RAGs and real-world AI agent applications.

Wan: Open and Advanced Large-Scale Video Generative Models

Multilingual Document Layout Parsing in a Single Vision-Language Model

Refine high-quality datasets and visual AI models

Machine Learning Engineering Open Book

A python tool that uses GPT-4, FFmpeg, and OpenCV to automatically analyze videos, extract the most interesting sections, and crop them for an improved viewing experience.

Steam Deck Plugin to apply Framegen mods to games by replacing DLSS DLL with FSR3 DLL

A minimal PyTorch implementation of probabilistic diffusion models for 2D datasets.

SoTA open-source TTS

A beautiful, powerful, self-hosted rom manager and player.

A MCP (model context protocol) server that gives the LLM access to and knowledge about relational databases like SQLite, Postgresql, MySQL & MariaDB, Oracle, and MS-SQL.

A high-performance algorithmic trading platform and event-driven backtester

[CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

A collection of MCP servers.

Create a USB Rubber Ducky like device using a Raspberry PI Pico

[AAAI 2025] Event-Enhanced Blurry Video Super-Resolution

[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"

Build Real-Time Knowledge Graphs for AI Agents

GoodbyeDPI (Türkiye için DNS değişikliği engelini bertaraf etme) (Windows)

SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.

Roo Code gives you a whole dev team of AI agents in your code editor.

Multi-modal OCR pipeline optimized for ML training (text, figure, math, tables, diagrams)

🚀 The fast, Pythonic way to build MCP servers and clients