JCodesMore/ai-website-cloner-template

Clone any website with one command using AI coding agents

What it solves

It allows users to recreate an existing website as a clean, modern Next.js application by providing a URL to an AI coding agent. This is particularly useful for migrating platforms (e.g., from WordPress to Next.js), recovering lost source code from a live site, or studying how professional sites are built.

How it works

The project provides a template and a set of instructions (a "skill") that AI coding agents use to execute a multi-phase pipeline:

  1. Reconnaissance: The agent takes screenshots and extracts design tokens and interaction behaviors.
  2. Foundation: It sets up fonts, colors, and global styles and downloads necessary assets.
  3. Component Specs: It creates detailed specification files containing exact CSS values and behaviors for each component.
  4. Parallel Build: Multiple builder agents work in parallel to create individual sections or components.
  5. Assembly & QA: The pieces are merged into a final page and checked against the original site using visual diffs.

Who it’s for

  • Developers looking to migrate legacy websites to a modern stack.
  • Site owners who have lost access to their original source code.
  • Learners who want to deconstruct production-level layouts and animations.

Highlights

  • Broad Agent Support: Compatible with Claude Code, Cursor, Windsurf, GitHub Copilot, Gemini CLI, and others.
  • Modern Tech Stack: Generates code using Next.js 16, React 19, Tailwind CSS v4, and shadcn/ui.
  • High Precision: Uses getComputedStyle() to ensure exact visual reproduction rather than guessing.
  • Automated Workflow: Includes a dedicated /clone-website command for supported AI agents.

Related

  • Project
    langchain-ai/langchain-nextjs-template

    A starter template for building AI applications with LangChain.js and Next.js, featuring implementations for streaming chat, RAG, and agentic workflows.

  • Project
    HKUDS/CLI-Anything

    CLI‑Anything is a Python framework that automatically generates agent‑friendly Click CLIs for any software, outputting JSON for easy parsing. It includes a 7‑phase generation pipeline (analyze → design → implement → test → document → publish) and a package manager called CLI‑Hub to browse, install, and run a growing catalog of pre‑built CLIs (e.g., GIMP, Blender, Zoom). The project targets AI agents (Claude Code, Cursor, OpenClaw, etc.) that need deterministic, composable command interfaces, and it ships with a comprehensive test suite and security hardenings.

  • Project
    vercel/next-evals-oss

    Next.js Evals is a Vercel‑maintained framework for automatically testing AI coding agents on real‑world Next.js tasks. It syncs eval fixtures from the `vercel/next.js` repo, runs agents in a Vercel sandbox, checks hidden assertions, records pass/fail, token usage, and cost, and exports a JSON leaderboard that powers the public Next.js evaluation site.

  • Project
    ConardLi/easy-agent

    A terminal-native coding agent built with TypeScript and Node.js that integrates LLMs with local file and shell tools for automated software development.

  • Project
    Shubhamsaboo/awesome-llm-apps

    Awesome LLM Apps is an Apache‑2.0‑licensed collection of 100+ ready‑to‑run AI agents, agent‑skills, and RAG pipelines. The repo groups templates into starter agents, advanced multi‑step agents, always‑on services, voice agents, generative‑UI agents, game‑playing bots, MCP‑enabled tools, and detailed RAG tutorials. Each entry ships with real code, security‑checked CI, and works with Claude, Gemini, GPT‑4/4o, DeepSeek, Llama, Qwen and other models. Users can add a skill in seconds (`npx skills add …`) or run a full agent in ~30 seconds (`pip install && streamlit run`). The project is maintained by Unwind AI and is free for commercial use.