Python

Qwen3-ASR is an open-source series of ASR models developed by the Qwen team at Alibaba Cloud, supporting stable multilingual speech/music/song recognition, language detection and timestamp prediction.

Converts profiling output to a dot graph.

Devon: An open-source pair programmer

A high-performance distributed training framework for Reinforcement Learning

Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.

THIS IS NOT THE OFFICIAL REPO - PLEASE SUBMIT PRs ETC AT: http://github.com/sqlalchemy/sqlalchemy

A linter for YAML files.

Modularized Implementation of Deep RL Algorithms in PyTorch

【PyTorch】Easy-to-use,Modular and Extendible package of deep-learning based CTR models.

QuantStart.com - QSTrader backtesting simulation engine.

PennyLane is an open-source quantum software platform for quantum computing, quantum machine learning, and quantum chemistry. Create meaningful quantum algorithms, from inspiration to implementation.

Simple tagging for django

Follow along with my AI Agents Masterclass videos! All of the code I create and use in this series on YouTube will be here for you to use and even build on top of!

Official implementation of Kimodo, a kinematic motion diffusion model for high-quality human(oid) motion generation.

A utility for managing proot containers.

自动化运维平台：CMDB、CD、DevOps、资产管理、任务编排、持续交付、系统监控、运维管理、配置管理

Adaptive Lighting custom component for Home Assistant

Digital Avatar Conversational System - Linly-Talker. 😄✨ Linly-Talker is an intelligent AI system that combines large language models (LLMs) with visual models to create a novel human-AI interaction method. 🤝🤖 It integrates various technologies like Whisper, Linly, Microsoft Speech Services, and SadTalker talking head generation system. 🌟🔬

A Dockerized python Script to fetch Garmin health data and populate that in a InfluxDB Database, for visualization long term health trends with Grafana

DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

A ~9M parameter LLM that talks like a small fish.

Clean, Robust, and Unified PyTorch implementation of popular Deep Reinforcement Learning (DRL) algorithms (Q-learning, Duel DDQN, PER, C51, Noisy DQN, PPO, DDPG, TD3, SAC, ASL)

Mirix is a multi-agent personal assistant designed to track on-screen activities and answer user questions intelligently. By capturing real-time visual data and consolidating it into structured memories, Mirix transforms raw inputs into a rich knowledge base that adapts to your digital experiences.

🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.

Entropy Based Sampling and Parallel CoT Decoding

✨ AsrTools: Smart Voice-to-Text Tool | Efficient Batch Processing | User-Friendly Interface | No GPU Required | Supports SRT/TXT Output | Turn your audio into accurate text in an instant!

ROS Wrapper for RealSense™ Cameras

Firmware patcher for Xiaomi routers

AnimateDiff for AUTOMATIC1111 Stable Diffusion WebUI