NextChat

One-click deployment made NextChat, formerly ChatGPT-Next-Web, one of the most forked AI projects on GitHub, with 88.6k stars and over 59k forks. The MIT-licensed client ships as a web PWA, a roughly 5 MB Tauri desktop app for macOS, Windows, and Linux, and an iOS app, all connecting to OpenAI, Claude, Google Gemini, DeepSeek, Azure, Baidu, ByteDance, Alibaba, and ChatGLM endpoints with user-supplied keys. Masks provide reusable prompt templates for building custom chat tools, and the app adds Model Context Protocol support behind an ENABLE_MCP flag, artifact generation and sharing, Markdown, LaTeX, and Mermaid rendering with code highlighting, and compatibility with self-hosted backends such as RWKV-Runner and LocalAI. All data stays in browser-local storage for privacy. Deploying a personal instance takes one click on Vercel or Zeabur plus an API key, or a desktop installer with no technical setup and no GPU. A paid enterprise edition adds brand customization, admin controls, knowledge base integration, and private deployment. It remains a default choice for spinning up a personal chat frontend in minutes.