firecrawl/open-lovable

🔥 Clone and recreate any website as a modern React app in seconds

What is Open Lovable?

Open Lovable is an example application built by the Firecrawl team. It lets you chat with an AI to build React apps instantly — you describe what you want, and the AI generates a working React app for you. It's a demonstration of a concept, and for a full cloud-based version, the README points to Lovable.dev.

How does it work?

Based on the README, the app uses:

  • Firecrawl – requires an API key (from firecrawl.dev) to power the core functionality.
  • An AI provider – you choose one of four LLMs: Google Gemini, Anthropic, OpenAI, or Groq. You provide the corresponding API key.
  • A sandbox provider – where the generated React app runs. You can pick Vercel (default) or E2B. For Vercel, you can authenticate via an OIDC token (auto-generated by vercel env pull) or a personal access token. For E2B, you need an E2B API key.
  • Optional: Morph API – speeds up edits ("Fast Apply") if you provide a Morph API key.

Setup steps (from the README)

  1. Clone the repo and install dependencies (pnpm install or npm/yarn).
  2. Create a .env.local file with the required keys:
    • FIRECRAWL_API_KEY (required)
    • One AI provider key (Gemini, Anthropic, OpenAI, or Groq)
    • Optional MORPH_API_KEY
    • Sandbox configuration (Vercel or E2B)
  3. Run pnpm dev (or npm/yarn equivalent) and open http://localhost:3000.

License

MIT.

Note: The README does not describe the internal architecture, the exact AI interaction flow, or how the generated apps are deployed — only the setup and the general purpose.

Related

  • Project
    google-labs-code/design.md

    A Node.js CLI and markdown‑based spec (`DESIGN.md`) for defining design tokens (colors, typography, spacing, component styles) that AI coding agents can read. It validates files, compares versions, and exports tokens to Tailwind or W3C token formats.

  • Project
    manaflow-ai/cmux

    cmux is a native macOS terminal built on Ghostty that adds vertical tabs, notification rings, an in‑app browser, SSH workspaces, and a programmable CLI to help developers monitor and orchestrate multiple AI coding agents such as Claude Code, Codex, and OpenCode.

  • Project
    QwenLM/qwen-code

    An open-source, multi-platform AI coding agent that automates development tasks like code reviews, bug fixing, and project navigation across terminals, IDEs, and chat applications.

  • Project
    charmbracelet/crush

    Crush is a terminal‑based AI coding assistant that lets you chat with any LLM, keep per‑project sessions, use language‑server data, and extend functionality via custom Model Context Protocol services—all configurable through a Bash‑style `crushrc` and available on all major OSes.