NanoGPT (124M) in 3 minutesModded-NanoGPT This repository hosts the NanoGPT speedrun, in which we (collaboratively|competitively) search for the fastest algorithm to use 8 NVIDIA H100 GPUs to train a language model that attains 3.28 cross-entropy loss on the FineWeb validation set. The target (3.28 validation loss on FineWeb) follows Andrej Karpathy's GPT-2 replication in llm.c, which attains that loss after running for 45 minutes. The speedrun code also descends from llm.c's PyTorch tr…
Full-throttle, wire-speed hardware implementation of Wireguard VPN, using low-cost Artix7 FPGA with opensource toolchain. If you seek security and privacy, nothing is private in our codebase. Our door is wide open for backdoor scrutiny, be it related to RTL, embedded, build, bitstream or any other aspect of design and delivery package. Bujrum!Wireguard FPGA Virtual Private Networks (VPNs) are the central and indispensable component of Internet security. They comprise a set of technologies that …
Next Generation Server Toolkit. Create web servers with everything you need and deploy them wherever you prefer.Nitro NoteYou’re viewing the v3 Alpha branch. For the current stable release, see Nitro v2. Nitro extends your Vite app with a production-ready server, designed to run anywhere. Add server routes, deploy across multiple platforms, and enjoy a zero-config experience. 📘 Docs (v3 Alpha): https://v3.nitro.build Contributing See Check out the Contribution Guide to get started. License Rel…
Klavis AI (YC X25): MCP integration layers that let AI agents use thousands of tools reliably. Klavis AI 📦 MCP integration layers that let AI agents use tools reliably at any scale 🎯 Choose Your Solution 📦 Strata Unified MCP Router One MCP server for AI agents to use tools reliably at any scale …
A context-aware AI assistant for your desktop. Ready to respond intelligently, seamlessly integrating multiple LLMs and MCP tools. 前往中文版本 » Every moment, Every place. Your AI - Everywhere Explore the docs » View Demo · Report Bug · Request Feature About Everywhere Everywhere is an interactive AI assistant with context-aware capabilities, featuring a sleek, modern UI and powerful integrated functionality. Unlike traditional AI tools, Everywhere…
CLI tool for configuring and monitoring Claude Code Claude Code Templates (aitmpl.com) Ready-to-use configurations for Anthropic's Claude Code. A comprehensive collection of AI agents, custom commands, settings, hooks, external integrations (MCPs), and project templates to enhance your development workflow. Browse & Install Components and Templates Browse All Templates - Interactive web interface to explore and install 100+ agents, commands, settings, hooks, and MCPs. 🚀 Quick In…
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.Qwen3-VL 💜 Qwen Chat | 🤗 Hugging Face | 🤖 ModelScope | 📑 Blog | 📚 Cookbooks | 📑 Paper is coming 🖥️ Demo | 💬 WeChat (微信) | 🫨 Discord | 📑 API | 🖥️ PAI-DSW Introduction Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date. This generation delivers comprehensive upgrades across the board: superior text understanding & …
An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before. Coze your way to AI Agent creation. Coze Studio • Feature list • Quickstart • Developer Guide English | 中文 What is Coze Studio? Coze Studio is an all-in-one AI agent development tool. Providing the latest large models and tools, various development modes and frameworks, Coze Studio offers the most convenient AI agent development environment, from dev…
🛍️ Typescript E-commerce Platform EverShop Documentation | Demo Introduction EverShop is a modern, TypeScript-first eCommerce platform built with GraphQL and React. Designed for developers, it offers essential commerce features in a modular, fully customizable architecture—perfect for building tailored shopping experiences with confidence and speed. Installation Using Docker You can get started with EverShop in minutes by using the…