Foundational Model for Speech Recognition Tasks

The swiss army knife of lossless video/audio editing

Keyvi - the key value index. It is an in-memory FST-based data structure highly optimized for size and lookup performance.

The original sources of MS-DOS 1.25, 2.0, and 4.0 for reference purposes

This package contains the original 2012 AlexNet code.

Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.

An AI agent that writes (actually useful) code for you

A library for advanced large language model reasoning

Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any open source LLM / VLM!

Democratizing Reinforcement Learning for LLMs

List of blocked domains

Amnezia VPN Client (Desktop+Mobile)

Frontier Multimodal Foundation Models for Image and Video Understanding

Hestia Control Panel | A lightweight and powerful control panel for the modern web.

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

Janus-Series: Unified Multimodal Understanding and Generation Models

chDB is an in-process OLAP SQL Engine 🚀 powered by ClickHouse

Bitcoin Core integration/staging tree

Whisper with Medusa heads

A Lightweight Recommendation System

The Fastest Deep Reinforcement Learning Library

Silero Models: pre-trained speech-to-text, text-to-speech and text-enhancement models made embarrassingly simple

MARS5 speech model (TTS) from CAMB.AI

ML-powered speech recognition directly in your browser

Official inference repo for FLUX.1 models

tiny vision language model

📚 Freely available programming books