Maze
A distributed framework for LLM agents
HYSEN LABS DIRECTORY
Curated AI & Machine Learning repositories with precise tags and practical analysis.
A distributed framework for LLM agents
A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.
Kosmos: An AI Scientist for Autonomous Discovery - An implementation and adaptation to be driven by Claude Code or API - Based on the Kosmos AI Paper - https://arxiv.org/abs/2511.02824
Framework that enables fine-tuning of vision-language grounding models on custom datasets
A Vulkan Raytracing framework for various bidirectional path tracing techniques
Run Claude Code, Codex, Antigravity, Cursor Agent and OpenCode as one runtime — persistent sessions, multi-agent councils, an OpenAI-compatible endpoint, an MCP server, and an ACP agent any editor can drive.
Less clutter, more clarity
Evaluating text-to-image/video/3D models with VQAScore
An AI companion that lives in Minecraft: summon it, talk to it, and it plans and acts on its own, mining, building, farming, fighting and crafting.
🍁 Sycamore is an LLM-powered search and analytics platform for unstructured data.
Code snippets and examples from the 100x Applied AI cohort lectures.
📖 Korean NLU Benchmark
Multi-backend CLI for executable markdown prompts. Run .md files against Claude, Codex, Gemini, or Copilot.
在 B 站视频页抓取字幕,预览后可复制 Markdown、下载字幕文件,并一键写入 Obsidian(Local REST API)。
Node Creative Coding / 3D / Image Processing tool inspired by Quartz Composer
All the source code for "Robot Learning: A Tutorial". Get involved to be featured in the next iteration!
A MCP server for the Discord integration. Enable your AI assistants to seamlessly interact with Discord. Enhance your Discord experience with powerful automation capabilities.
WoWAnalyzer is a tool to help you analyze and improve your World of Warcraft raiding performance through various relevant metrics and gameplay suggestions.
A collection of agent skills for designers who prototype and build with AI coding tools. These skills encode design process so AI follows a structured path instead of producing random output.
NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process communication and coordination overheads by allowing programmers to perform one-sided communication from within CUDA kernels and on CUDA streams.