vgpu
Modular cross-runtime WebGPU library for shaders, 3D scenes, GPU tensors, neural networks, and math viz
HYSEN LABS DIRECTORY
Curated repositories with precise taxonomy, verified metadata and practical context.
Modular cross-runtime WebGPU library for shaders, 3D scenes, GPU tensors, neural networks, and math viz
从无名小卒到大模型(LLM)大英雄~ 欢迎关注后续!!!
Deep Reinforcement Learning: Zero to Hero!
An open-source academic paper management tool.
Automated YouTube Shorts pipeline: news → script → AI visuals → voiceover → captions → upload
This repository helps you learn Python and Machine Learning from scratch.
The Next-gen Open Source learning platform for everyone ✨
simple neural network library in C99
Helping AI Agent become an awesome practical hacker!
👻 Proxy API gateway for Kiro IDE & CLI (Amazon Q Developer / AWS CodeWhisperer). Use free Claude models with any client.
a real-time and empathetic memory system for voice assistants
The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.
Master the fundamentals of machine learning, deep learning, and mathematical optimization by building key concepts and models from scratch using Python.
A Python package to assess and improve fairness of machine learning models.
Google Ads MCP + Meta Ads MCP + GA4 in one server for Claude, ChatGPT, Cursor & n8n — 250+ tools, hosted remote MCP, OAuth login, no API keys. By Ryze AI.
A fast directory-first photo gallery website, with rich UI, optimized for running on low resource servers (especially on raspberry pi)
MCP server that enables AI assistants to interact with Google Gemini CLI, leveraging Gemini's massive token window for large file analysis and codebase understanding
Feature engineering and selection open-source Python library compatible with sklearn.
An agentic company research tool powered by LangGraph and Tavily that conducts deep diligence on companies using a multi-agent framework. It leverages Google's Gemini 2.5 Flash and OpenAI's GPT-5.1 on the backend for inference.
Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, llama.cpp, ik_llama) and model-agnostic. Currently shipping Qwen3.6-27B Qwen3.6 35B Gemma 4 26B Gemma 4 31B configs for 1 and 2 cards.