Transformer Explained Visually: Learn How LLM Transformer Models Work with Interactive Visualization

An incremental parsing system for programming tools

State-of-the-Art Text Embeddings

NVSentinel is a cross-platform fault remediation service designed to rapidly remediate runtime node-level issues in GPU-accelerated computing environments

A Claude Code skill to generate images with Nano Banana

Tooling for optimized, validated, and reproducible GPU-accelerated AI runtime in Kubernetes

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

AI agents running research on single-GPU nanochat training automatically

🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using Agentic Retrieval 🔄.

Lightweight coding agent that runs in your terminal

An open-source, code-first Go toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

A security-focused library OS supporting kernel- and user-mode execution

CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation

Safe rust wrapper around CUDA toolkit

Fast, small, and fully autonomous AI personal assistant infrastructure, ANY OS, ANY PLATFORM — deploy anywhere, swap anything 🦀

Tiny, Fast, and Deployable anywhere — automate the mundane, unleash your creativity

Distributed KV cache scheduling & offloading libraries

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

OpenClaw-RL: Train any agent simply by talking

happy happy happyclaw~

The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞

基于 Garmin 数据，通过专业的跑力（VDOT）分析、心率区间分布、配速趋势等多维度数据，为跑者提供科学的训练建议和数据洞察。

Flash Attention in ~100 lines of CUDA (forward pass only)

A Model Context Protocol (MCP) server that enables secure interaction with MySQL databases

OpenAI ChatGPT, GPT-5, GPT-Image-1, Whisper API clients for Go

A Model Context Protocol server that provides read-only access to MySQL databases. This server enables LLMs to inspect database schemas and execute read-only queries.

AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pods

Official Repository of "LLM × DATA" Survey Paper

Official Kubernetes Operator for ClickHouse®