msoftware

DIffUCO

alloy-voice-assistant

xlstm

Official repository of the xLSTM.

pico-cookbook

Recipes for on-device voice AI and local LLM

gpt-computer-assistant

gpt-4o for windows, macos and linux

Midasv2_1_small-TFLite-Inference

Python scripts to perform monocular depth estimation using Python with the Midas v2.1 small Tensorflow Lite model.

EasyAnimate

📺 An End-to-End Solution for High-Resolution and Long Video Generation Based on Transformer Diffusion

raptor

The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

ChatTTS

ChatTTS is a generative speech model for daily dialogue.

sqlite-utils

Python CLI utility and library for manipulating SQLite databases

DenseDepth

High Quality Monocular Depth Estimation via Transfer Learning

ijepa

Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive architecture."

VectorHub

VectorHub is a free, open-source learning website for people (software developers to senior ML architects) interested in adding vector retrieval to their ML stack.

llama3-from-scratch

llama3 implementation one matrix multiplication at a time

qdrant

Qdrant - High-performance, massive-scale Vector Database for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

MetaGPT

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

CDFormer

Reinforcement-Learning

Friend

AI wearable necklace

yt-dlp

A feature-rich command-line audio/video downloader

h2ogpt

Private chat with local GPT with document, images, video, etc. 100% private, Apache 2.0. Supports oLLaMa, Mixtral, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://codellama.h2o.ai/

xlstm

my attempts at implementing various bits of Sepp Hochreiter's new xLSTM architecture

PyxLSTM

PyxLSTM is a Python library that provides an efficient and extensible implementation of the Extended Long Short-Term Memory (xLSTM) architecture. xLSTM enhances the traditional LSTM by introducing exponential gating, memory mixing, and a matrix memory structure, enabling improved performance and scalability for sequence modeling tasks.

prometheus-eval

Evaluate your LLM's response with Prometheus 💯

puter

🌐 The Web OS! Free, Open-Source, and Self-Hostable.

tiny-world-map

tinyworldmap is a tiny world map for offline-first and low-bandwidth web apps

qrank

Wikidata's QRank as a SQLite DB.

wikidata-qrank

Ranking signals for Wikidata

maid

Maid is a cross-platform Flutter app for interfacing with GGUF / llama.cpp models locally, and with Ollama and OpenAI models remotely.

pragmatic-drag-and-drop

Fast drag and drop for any experience on any tech stack