Open one HTML file and you get a fully-featured, internet-aware, programmable, extensible AI agent — multi-turn chat, tool calls, Python sandbox, web search, skills, context compaction, long-term memory, file operations, cloud sync — all running on a single page.

No backend. No npm install. No Docker. Just one .html that carries an entire universe.

打开一个 HTML 文件，即可获得一个功能齐全、感知互联网、可编程、可扩展的 #AI 代理——多轮聊天、工具调用、Python 沙箱、网络搜索、技能、上下文压缩、长期记忆、文件操作、云同步——所有这些都在单个页面上运行。

没有后端，无需 npm install ，无需 Docker。只有一个网页 .html ，却承载着整个宇宙。

See also:

• https://github.com/Sparky579/MossChat Browser based chat client for your own model API keys. Keys, chats, files, and settings stay in the browser.
• https://github.com/xqdoo00o/chatgpt-web 部署一个HTML文件即可使用，支持复制/更新/刷新会话，语音输入，朗读等功能，以及众多自定义选项。支持搜索会话，深色模式，自定义头像，快捷键，多语言，环境变量，PWA应用，API额度显示等。
• LocalGPT: a html page for you to use GPT API LocalGPT is a one-page chat application that allows you to interact with OpenAI's GPT-3.5 API without the need for a server, extra libraries, or login accounts.
• https://github.com/jimliddle/privatellmlens PrivateLLMLens is a single-file browser interface for local Ollama, llama.cpp and optional in-browser WebGPU models. It works on desktop and Android/Termux without an application backend.